Detection of Abnormalities in Brain using Machine Learning in Medical Image Analysis

Medical image analysis has witnessed remarkable advancements, even surpassing human-level performance in recent years, driven by the rapid development of advanced deep-learning algorithms. However, when the inference dataset slightly differs from what the model has seen during one-time training, the model performance is greatly compromised. The situation requires restarting the training process using both the old and the new data, which is computationally costly, does not align with the human learning process, and imposes storage constraints and privacy concerns. Alternatively, continual learning has emerged as a crucial approach for developing unified and sustainable deep models to deal with new classes, tasks, and the drifting nature of data in non-stationary environments for various application areas. Continual learning techniques enable models to adapt and accumulate knowledge over time, which is essential for maintaining performance on evolving datasets and novel tasks. Owing to its popularity and promising performance, it is an active and emerging research topic in the medical field and hence demands a survey and taxonomy to clarify the current research landscape of continual learning in medical image analysis. This systematic review paper provides a comprehensive overview of the state-of-the-art in continual learning techniques applied to medical image analysis. We present an extensive survey of existing research, covering topics including catastrophic forgetting, data drifts, stability, and plasticity requirements. Further, an in-depth discussion of key components of a continual learning framework, such as continual learning scenarios, techniques, evaluation schemes, and metrics, is provided. Continual learning techniques encompass various categories, including rehearsal, regularization, architectural, and hybrid strategies. We assess the popularity and applicability of continual learning categories in various medical sub-fields like radiology and histopathology. Our exploration considers unique challenges in the medical domain, including costly data annotation, temporal drift, and the crucial need for benchmarking datasets to ensure consistent model evaluation. The paper also addresses current challenges and looks ahead to potential future research directions.

Glaucoma is a serious condition of the optic nerve, resulting in loss of eyesight. A sight-threatening disease, it causes impairment of the optic nerve. Glaucoma detection is an important field of medical image analysis. Nowadays, the scope of machine learning in medical image analysis as well as glaucoma detection is drawing attention from the clinical point of view. The ophthalmologist can avail the benefit of one more opinion through computer-aided diagnosis. The algorithm of machine learning can provide accuracy that is one step ahead for detection of glaucoma. Hence from the accuracy point of view, machine learning techniques can be a beneficial experience for the ophthalmologist. Identification of symptoms for glaucoma and glaucoma affected retinal images is a very important task. Machine learning algorithm works on the symptoms and based on the algorithm, it can classify glaucomatous eyes. Machine learning algorithm needs relevant features for identifying the symptom of glaucoma. For extracting accurate features, good quality image is important. Hence, here we mainly focus on the approach used by machine learning techniques for automatic detection of glaucoma. Retinal image acquisition, image preprocessing techniques, feature extraction, classification of symptoms of glaucoma affected image, and evaluating the performance are the important steps in machine learning techniques. Deep learning approach is an also elaborate process for detection of glaucoma in retinal images.

The incorporation of physical information in machine learning frameworks is transforming medical image analysis (MIA). Integrating fundamental knowledge and governing physical laws not only improves analysis performance but also enhances the model’s robustness and interpretability. This work presents a systematic review of over 100 articles on the utility of PINNs dedicated to MIA (PIMIA) tasks. We propose a unified taxonomy to investigate what physics knowledge and processes are modeled, how they are represented, and the strategies to incorporate them into MIA models. We delve deep into a wide range of image analysis tasks, from imaging, generation, prediction, inverse imaging (super-resolution and reconstruction), registration, and image analysis (segmentation and classification). For each task, we thoroughly examine and present the central physics-guided operation, the region of interest (with respect to human anatomy), the corresponding imaging modality, the datasets used for model training, the deep network architectures employed, and the primary physical processes, equations, or principles utilized. Additionally, we also introduce a novel metric to compare the performance of PIMIA methods across different tasks and datasets. Based on this review, we summarize and distill our perspectives on the challenges, and highlight open research questions and directions for future research.

Medical image analysis using deep neural networks (DNN) has demonstrated state-of-the-art performance in image classification and segmentation tasks, aiding disease diagnosis. The accuracy of the DNN is largely governed by the quality and quantity of the data used to train the model. However, for the medical images, the critical security and privacy concerns regarding sharing of local medical data across medical establishments precludes exploiting the full DNN potential for clinical diagnosis. The federated learning (FL) approach enables the use of local model's parameters to train a global model, while ensuring data privacy and security. In this paper, we review the federated learning applications in medical image analysis with DNNs, highlight the security concerns, cover some efforts to improve FL model performance, and describe the challenges and future research directions.

With the rise of deep learning, medical image analysis has undergone fundamental change, presenting new possibilities to physicians in terms of achieving higher accuracy more efficiently, and greater automation in disease diagnosis and prognosis. In this paper, we discuss recent progress in utilizing deep learning techniques such as convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), and transformer-based model for medical image analysis. Image classification, segmentation, and anomaly detection in modalities such MRI, CT, Xray, and ultrasound have been strongly improved by these architectures. Yet, such progress brings challenges, namely scarcity of sufficient data, interpretability of models, computational intensity, and robust generalization to diverse clinical datasets. At the same time regulatory concerns and ethical questions on the use of AI diagnostics are still constraining large scale adoption. This paper provides a comprehensive review of state-of-the art deep learning models in medical imaging, reviews the current limitations, and envisions future research directions in federated learning, explainable AI, and quantum enhanced deep learning. Such insights are intended to guide researchers and clinicians in the optimization of AI driven medical image analysis for optimized patient care and clinical decision making.

Not-so-supervised: A survey of semi-supervised, multi-instance, and transfer learning in medical image analysis.

Deep learning models in medical image analysis

Recent developments in remote sensing research have resulted in a large amount of variability in the data provided by researchers. Synthetic aperture radar (SAR) is a tool used to measure surface deformation and assess changes in the Earth’s surface. Here, we consider the usefulness of Interferometric Synthetic Aperture Radar (InSAR) in assessing past volcanic activity as a key to learning the characteristics of the deformation around a volcano. The Hantangang River volcanic field (HRVF) is a geoheritage site in the Korean Peninsula that has interesting geological characteristics. This volcanic field has formed along 110 km of the paleochannel of the Hantangang River. Since the eruptions occurred from 0.15 to 0.51 Ma, the source is limited, which has raised interest in the assessment of volcanic landforms. The recent integration of machine learning and InSAR processing has shown promising results for many purposes, such as classifying, modeling, and detecting surface deformation. To examine the future impact based on information from the past, we utilized a synthetic interferogram with the Okada model and transferred it to a machine learning algorithm. The synthetic interferogram was formed based on Sentinel-1 C-band satellite data to simulate the deformation phases. The orbital errors, the topographical data errors, and the atmospheric effect were also simulated and added to the synthetic interferogram to enrich the learning input. A convolutional neural network (CNN) trained with the unwrapped simulated interferogram data and its performance was evaluated. Our proposed method exhibits the capability to detect volcanic activity’s deformation patterns with synthetic interferogram data. The results show that an overall accuracy of more than 80% was achieved using the CNN algorithms on the validation dataset. This study is the first to use machine learning approaches for detecting prehistorical volcanic deformation and demonstrates potential techniques for developing an approach based on satellite imagery. In addition, this study has introduced the possibility of developing a rapid detection of surface deformation using InSAR data based on a machine learning approach.

In the field of medicine, with the introduction of computer systems that can collect and analyze massive amounts of data, many non-invasive diagnostic methods are being developed for a variety of conditions. In this study, our aim is to develop a non-invasive method of classifying respiratory sounds that are recorded by an electronic stethoscope and the audio recording software that uses various machine learning algorithms.In order to store respiratory sounds on a computer, we developed a cost-effective and easy-to-use electronic stethoscope that can be used with any device. Using this device, we recorded 17,930 lung sounds from 1630 subjects.We employed two types of machine learning algorithms; mel frequency cepstral coefficient (MFCC) features in a support vector machine (SVM) and spectrogram images in the convolutional neural network (CNN). Since using MFCC features with a SVM algorithm is a generally accepted classification method for audio, we utilized its results to benchmark the CNN algorithm. We prepared four data sets for each CNN and SVM algorithm to classify respiratory audio: (1) healthy versus pathological classification; (2) rale, rhonchus, and normal sound classification; (3) singular respiratory sound type classification; and (4) audio type classification with all sound types. Accuracy results of the experiments were; (1) CNN 86%, SVM 86%, (2) CNN 76%, SVM 75%, (3) CNN 80%, SVM 80%, and (4) CNN 62%, SVM 62%, respectively.As a result, we found out that spectrogram image classification with CNN algorithm works as well as the SVM algorithm, and given the large amount of data, CNN and SVM machine learning algorithms can accurately classify and pre-diagnose respiratory audio.

Findings from machine learning in clinical medical imaging applications – Lessons for translation to the forensic setting

Healthcare sectors have evolved over the years to remain as one of the most demanding and important aspects of human lives requiring immediate services and attention in difficult times but the entire process is quite tedious and time-consuming when performed by medical experts. However, with the advent of Artificial Intelligence based machine learning or deep learning techniques, the medical image analysis task became quite smoother, faster, and efficient delivering more optimized performances. This manuscript briefs us about the various deep learning techniques and methodologies being applied till now in the domain of medical image processing besides emphasizing the overview of recent advances and overall contributions being made in this field along with its associated challenges. It also throws light on the future perspective to overcome those challenges specifically using better and innovative approaches.

Optimized machine learning approaches for identifying vertical temperature gradient on ballastless track in natural environments

Classification and prediction tasks are common in health research. With the increasing availability of vast health data repositories (e.g. electronic medical record databases) and advances in computing power, traditional statistical approaches are being augmented or replaced with machine learning (ML) approaches to classify and predict health outcomes. ML describes the automated process of identifying ("learning") patterns in data to perform tasks. Developing an ML model includes selecting between many ML models (e.g. decision trees, support vector machines, neural networks); model specifications such as hyperparameter tuning; and evaluation of model performance. This process is conducted repeatedly to find the model and corresponding specifications that optimize some measure of model performance. ML models can make more accurate classifications and predictions than their statistical counterparts and confer greater flexibility when modelling unstructured data or interactions between covariates; however, many ML models require larger sample sizes to achieve good classification or predictive performance and have been criticized as "black box" for their poor transparency and interpretability. ML holds potential in family medicine for risk profiling of patients' disease risk and clinical decision support to present additional information at times of uncertainty or high demand. In the future, ML approaches are positioned to become commonplace in family medicine. As such, it is important to understand the objectives that can be addressed using ML approaches and the associated techniques and limitations. This article provides a brief introduction into the use of ML approaches for classification and prediction tasks in family medicine.

Whether tracking patient progress for clinical decision making, or investigating novel therapies, automated analysis of Computed Tomography (CT) imaging data is essential for the future of digital radiomics. In digital radiomics, as in all medical imaging, well annotated data is scarce, whereas unlabelled images are relatively plentiful. In other fields of image processing and medical imaging, the application of self-supervised learning (SSL) to large quantities of unlabelled data has resulted in great strides forward for fast, scalable, and interpretable image analysis. In this work we present a new approach applying SSL to CT imaging data which allows for: 1) Improved performance on image classification tasks, based on 2) dramatically reduced quantity of annotated CT imaging data, whilst also 3) enabling easy exploration and interpretation of the image regions. We applied a selection of self-supervised approaches (BYOL, DINO, SimCLR, & inpainting) to CT imaging data. Because the high dimensionality of CT data prevents us from using them directly to out-of the box SSL models, we adopt a 3D patching approach to reduce the dimensionality of the neural net input, and process each patch independently. We train our self-supervised models on public datasets (DeepLesion, NSCLC), and we specialize these models for tumor classification tasks that we evaluate on AstraZeneca sponsored clinical trials. The specialization is done in two different ways: 1) we use the pre-trained SSL model as an encoder that transforms the images of the clinical study into embeddings, on which we apply supervised classification models; 2) we use transfer learning to fine-tune supervised classification models that take the patches directly as inputs. We find that self-supervised pre-training significantly improves the accuracy on tumor classification tasks compared against a supervised learning baseline. Additionally, using the SSL embeddings we build an interactive map of CT imaging data enabling quick and intuitive inspection of the relevant regions. Our findings show that SSL constitutes an important tool for medical imaging analysis. SSL results in models that generalize better, and enable improved downstream interpretability and predictions. Furthermore, well trained SSL models can be re-applied to multiple indications because they are pre-trained on broad and diverse CT imaging data. Citation Format: Leon Fedden, Zhenning Zhang, Khan Baykaner, Qin Li, Lucas Bordeaux. DIME-CT: Self-supervised learning for medical image analysis using patch-based embeddings [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 1937.

Performance optimization of wireless networks is typically complicated because of high computational complexity and dynamic channel conditions. Considering a specific case, the recent introduction of intelligent reflecting surface (IRS) can reshape the wireless channels by controlling the scattering elements' phase shifts, namely, passive beamforming. However, due to the large size of scattering elements, the IRS's beamforming optimization becomes intractable. In this article, we focus on machine learning (ML) approaches for complex optimization problems in wireless networks. ML approaches can provide flexibility and robustness against uncertain and dynamic systems. However, practical challenges still remain due to slow convergence in offline training or online learning. This motivated us to design a novel optimization-driven ML framework that exploits the efficiency of model-based optimization and the robustness of model-free ML approaches. Splitting the control variables into two parts allows one part to be updated by the outer loop ML approach while the other part is solved by the inner loop optimization. The case study in IRS-assisted wireless networks confirms that the optimization-driven ML framework can improve learning efficiency and the reward performance significantly compared to conventional model-free ML approaches.