Deep Random Forests for Small Sample Size Prediction with Medical Imaging Data

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.

Deep learning has revolutionized the detection of diseases and is helping the healthcare sector break barriers in terms of accuracy and robustness to achieve efficient and robust computer-aided diagnostic systems. The application of deep learning techniques empowers automated AI-based utilities requiring minimal human supervision to perform any task related to medical diagnosis of fractures, tumors, and internal hemorrhage; preoperative planning; intra-operative guidance, etc. However, deep learning faces some major threats to the flourishing healthcare domain. This paper traverses the major challenges that the deep learning community of researchers and engineers faces, particularly in medical image diagnosis, like the unavailability of balanced annotated medical image data, adversarial attacks faced by deep neural networks and architectures due to noisy medical image data, a lack of trustability among users and patients, and ethical and privacy issues related to medical data. This study explores the possibilities of AI autonomy in healthcare by overcoming the concerns about trust that society has in autonomous intelligent systems.

Hyperspectral imaging is a rising imaging modality in the field of medical applications, and the combination of both spectral and spatial information provides wealth information for cell classification. In this paper, deep convolutional neural network (CNN) is employed to achieve blood cell discrimination in medical hyperspectral images (MHSI). As a deep learning architecture, CNNs are expected to get more discriminative and semantic features, which effect classification accuracy to a certain extent. Experimental results based on two real medical hyperspectral image data sets demonstrate that cell classification using CNNs is effective. In addition, compared to traditional support vector machine (SVM), the proposed method, which jointly exploits spatial and spectral features, can achieve better classification performance, showcasing the CNN-based methods' tremendous potential for accurate medical hyperspectral data classification.

Introduction: The importance of neonatal health monitoring lies in early detection, and thus, addressing NICU (Neonatal Incentive Care Unit) patients with timely medical treatment. Current predictive models typically use only either medical imaging or sensor data, limiting their efficiency for real time detection of multiple neonatal conditions. To overcome this limitation, we introduce NeoCoD (Neonatal Cause of Disease Predictor), an IoT-based predictive analytics system that combines physiological markers based on sensor data with medical imaging data to better assess the health of newborns. Objectives: The main purpose of this study was to design a hybrid deep learning model using ResNet50 (Residual Neural Network) for medical images feature extraction and Long Short-Term Memory (LSTM) for the temporal analysis of IoT based sensor data. The dataset contains 7132 samples of 270 neonates collected from Sparsh Medical Hospital, Ahmedabad, Dr. Babasaheb Ambedkar Hospital, Mumbai, and publicly available neonatal health data. We colligate neonatal diseases (e.g., Neonatal Respiratory Distress Syndrome (NRDS), Neonatal Sepsis, Jaundice, Hypothermia, Hypoglycemia, Neonatal Pneumonia, Neonatal Apnea, Perinatal Asphyxia, Neonatal Meningitis, Neonatal Encephalopathy, Hyperbilirubinemia, Low Birth Weight Complications) for our study. Methods: The NeoCoD model pipeline consists of the following multi stages: data preprocessing, feature engineering, model training and performance evaluation. Feature scaling: the feature scaling was performed and rescaled the features to preprocess the information. We trained the model with categorical cross-entropy loss, Adam optimizer and regularization methods like dropout (0.3) layer and batch normalization. For comparing the performance of NeoCoD with ne trivial solutions, Random Forest and SVM models, accuracy, precision, recall, and F1-score are used. Results: Experimental results show that NeoCoD considerably outperforms traditional models with accuracy of 92.5% against Random Forest (87.3%) and SVM (84.5%). This model is capable of rapid multimodal processing and prediction on incoming data, providing real-time predictions with 2 seconds response time which makes it particularly suitable for NICU applications. Conclusions: These results establish NeoCoD as a high-accuracy, scalable neonatal health monitoring system for infant dieses prediction at earlier stage. Going forward, work will center on increasing generalisability across different hospital contexts, increasing computational efficiency, and improving interpretability for clinical decision-making.

The aim of the present work is to present the new software Multimod Data Manager and to show applications in the planning and monitoring of complex skeletal reconstructions in orthopedic oncology. The DataManager allows the full integration of different kind of data, particularly medical imaging data, both static as CT, SPECT or MRI, or time-varying as fluoroscopy or dynamic MRI, with motion analysis data, but also 3D computer and finite element models of bones, joints and also soft tissues. All the data can be visualized with highly interactive and specialized modalities and can be integrated to offer a complete representation of the patient anatomy. Several algorithms are implemented to allow registration and synchronization of the data. A fully 3D environment is offered to the surgeon to navigate inside the medical imaging dataset. To exemplify the use of the software we document in this paper the data processing used to investigate different specific clinical cases in the field of orthopedic oncology.

Segmentation of fused MR and CT images using DL-CNN with PGK and NLEM filtered AACGK-FCM

Radiological images, including X-rays, MRI, and CT scans, are essential modalities for disease diagnosis. However, the complexity of medical image data presents significant challenges in developing accurate and reliable classification models within the field of radiology. This study proposes a hybrid model that integrates an Autoencoder with a Random Forest classifier for disease classification based on radiological images. The Autoencoder is utilized to extract deep feature representations from the images, while the Random Forest serves as a robust classification algorithm. The research workflow involves preprocessing radiological image data to ensure quality and consistency, developing and training the Autoencoder to generate meaningful feature representations, and implementing the Random Forest as the classification model using the features extracted by the Autoencoder. The performance of the proposed hybrid model is evaluated by comparing it with baseline approaches, such as convolutional neural networks (CNNs) and standalone Random Forest models, using evaluation metrics including accuracy, sensitivity, and specificity, which are critical for assessing classification performance in medical imaging. This research aims to advance artificial intelligence applications in medical imaging, specifically for supporting disease diagnosis. The proposed model is anticipated to provide an efficient and reliable solution for processing radiological image data, thereby enhancing diagnostic capabilities and supporting clinical decision-making in the healthcare sector. The integration of deep feature extraction with robust classification is expected to address existing challenges in medical image analysis and contribute to the development of more effective diagnostic tools.

Multimodal imaging is gaining in importance in the field of personalized medicine and can be described as a current trend in medical imaging diagnostics. The segmentation, classification and analysis of tissue structures is essential. The goal of this study is the evaluation of established segmentation methods on different medical image data sets acquired with different diagnostic procedures. Established segmentation methods were implemented using the latest state of the art and applied to medical image data sets. In order to benchmark the segmentation performance quantitatively, medical image data sets were superimposed with artificial Gaussian noise, and the mis-segmentation as a function of the image SNR or CNR was compared to a gold standard. The evaluation of the image segmentation showed that the best results of pixel-based segmentation (< 3%) can be achieved with methods of machine learning, multithreshold and advanced level-set method - even at high artificial noise (SNR< 18). Finally, the complexity of the object geometry and the contrast of the ROI to the surrounding tissue must also be considered to select the best segmentation algorithm.

Wavelets have shown significant promise for medical image decomposition and artifact pre-processing by representing inputs via shifted and scaled components of a specified mother wavelet function. However, wavelets could also be leveraged within deep neural networks as activation functions for neurons (called wavelons) in the hidden layer. Integrating wavelons into a convolutional neural network architecture (termed a “wavelon network” (WN)) offers additional flexibility and stability during optimization, but the resulting model complexity has caused it to be limited to low-dimensional applications. Towards addressing these issues, we present the Residual Wavelon Convolutional Network (RWCN), a novel integrated WN architecture that employs weighted skip connections (to enable residual learning) together with image convolutions and wavelet activation functions to more efficiently capture high-dimensional disease response-specific patterns from medical imaging data. In addition to developing the analytical basis for wavelet activation functions as used in this work, we implemented RWCNs by adapting the popular VGG and ResNet architectures. Evaluation was conducted within three different challenging clinical problems: (a) predicting pathologic complete response (pCR) to neoadjuvant chemoradiation via 153 pre-treatment T2-weighted (T2w) MRI scans in rectal cancers, (b) evaluating pCR after chemoradiation via 100 post-treatment T2w MRIs in rectal cancers, as well as (c) risk stratifying patients who will or will not require surgery after aggressive medication in Crohn’s disease using 73 baseline MRI scans. In comparison to 4 state-of-the-art alternative models (VGG-16, VGG-19, ResNet-18, ResNet-50), RWCN architectures yielded significantly improved and more efficient classifier performance on unseen data in multi-institutional validation cohorts (hold-out accuracies of 0.82, 0.85, and 0.88, respectively).KeywordsWavelet networkResidual learningConvolutional neural networkDeep learningDisease response

Digital medical images can be viewed as digital representations of real physical tissue properties that are convenient for handling, storing, transmitting, retrieving, and analyzing image information. In order to perform feature extraction/identification/classification from high-dimensional medical data, we need dimensionality reduction (DR), which can be achieved by identifying the statistical patterns in medical image data with highlighting their similarities and dissimilarities. Here, the dimension of medical images is the total number of pixels in the image. In DR, we try to find an useful representation of reduced dimensionality in high-dimensional data, which minimizes information loss by maximizing local data variance. Given medical image data, the key challenging issue is how can we efficiently extract a low-dimensional latent structure? Various dimension reduction techniques have been developed to process the high-dimensional data where the intrinsic dimensions are assumed to be much lower. In the very ideal case, data can be regressed linearly and DR can be performed by principal component analysis. This chapter explains the theories, principles, and practices of DR techniques.

In this paper we describe the technologies and experimental results for the medical retrieval task and automatic annotation task. We combine textual and content-based approaches to retrieve relevant medical images. The content-based approach containing four image features and the text-based approach using word expansion are developed to accomplish these tasks. Experimental results show that combining both the content-based and text-based approaches is better than using only one approach. In the automatic annotation task we use Support Vector Machines (SVM) to learn image feature characteristics for assisting the task of image classification. Based on the SVM model, we analyze which image feature is more promising in medical image retrieval. The results show that the spatial relationship between pixels is an important feature in medical image data because medical image data always has similar anatomic regions. Therefore, image features emphasizing spatial relationship have better results than others.

Three-dimensional (3D) printing and medical imaging have a complementary association, the benefits and application areas of which are increasingly documented and further illustrated in this journal publication. Medical imaging data can be appropriately processed (i.e. segmented) to provide the geometric information from which accurate and realistic 3D medical models can be generated. The resulting models can be printed in a range of different materials to suit their use as phantoms in medical radiation and imaging studies, for medical imaging education and training or patient communication.

The 2014 workshop on medical computer vision (MCV): algorithms for big data took place in Cambridge, MA, USA in connection with MICCAI (Medical Image Computing for Computer Assisted Intervention). It is the fourth MICCAI MCV workshop after those held in 2010, 2012 and 2013 with another edition held at CVPR 2012. This workshop aims at exploring the use of modern computer vision technology in tasks such as automatic segmentation and registration, localisation of anatomical features and extraction of meaningful visual features. It emphasises questions of harvesting, organising and learning from large-scale medical imaging data sets and general-purpose automatic understanding of medical images. The workshop is especially interested in modern, scalable and efficient algorithms which generalise well to previously unseen images.The strong participation in the workshop of over 80 persons shows the importance of and interest in Medical Computer Vision. This overview article describes the papers presented in the workshop as either oral presentations or short presentations and posters. It also describes the invited talks and the results of the VISCERAL session in the workshop on the use of big data in medical imaging.

Optimal Deep Neural Network model based multimodality fused medical image classification

The need for medical image encryption is increasingly pronounced, for example, to safeguard the privacy of the patients' medical imaging data. In this article, a novel deep learning-based key generation network (DeepKeyGen) is proposed as a stream cipher generator to generate the private key, which can then be used for encrypting and decrypting of medical images. In DeepKeyGen, the generative adversarial network (GAN) is adopted as the learning network to generate the private key. Furthermore, the transformation domain (that represents the "style" of the private key to be generated) is designed to guide the learning network to realize the private key generation process. The goal of DeepKeyGen is to learn the mapping relationship of how to transfer the initial image to the private key. We evaluate DeepKeyGen using three data sets, namely, the Montgomery County chest X-ray data set, the Ultrasonic Brachial Plexus data set, and the BraTS18 data set. The evaluation findings and security analysis show that the proposed key generation network can achieve a high-level security in generating the private key.