Shifting to machine supervision: annotation-efficient semi and self-supervised learning for automatic medical image segmentation and classification.

Advancements in clinical treatment are increasingly constrained by the limitations of supervised learning techniques, which depend heavily on large volumes of annotated data. The annotation process is not only costly but also demands substantial time from clinical specialists. Addressing this issue, we introduce the S4MI (Self-Supervision and Semi-Supervision for Medical Imaging) pipeline, a novel approach that leverages advancements in self-supervised and semi-supervised learning. These techniques engage in auxiliary tasks that do not require labeling, thus simplifying the scaling of machine supervision compared to fully-supervised methods. Our study benchmarks these techniques on three distinct medical imaging datasets to evaluate their effectiveness in classification and segmentation tasks. Notably, we observed that self-supervised learning significantly surpassed the performance of supervised methods in the classification of all evaluated datasets. Remarkably, the semi-supervised approach demonstrated superior outcomes in segmentation, outperforming fully-supervised methods while using 50% fewer labels across all datasets. In line with our commitment to contributing to the scientific community, we have made the S4MI code openly accessible, allowing for broader application and further development of these methods. The code can be accessed at https://github.com/pranavsinghps1/S4MI .

Compressed Sensing for Biomedical Photoacoustic Imaging: A Review.

Photoacoustic imaging (PAI) is a rapidly developing emerging non-invasive biomedical imaging technique that combines the strong contrast from optical absorption imaging and the high resolution from acoustic imaging. Abnormal biological tissues (such as tumors and inflammation) generate different levels of thermal expansion after absorbing optical energy, producing distinct acoustic signals from normal tissues. This technique can detect small tissue lesions in biological tissues and has demonstrated significant potential for applications in tumor research, melanoma detection, and cardiovascular disease diagnosis. During the process of collecting photoacoustic signals in a PAI system, various factors can influence the signals, such as absorption, scattering, and attenuation in biological tissues. A single ultrasound transducer cannot provide sufficient information to reconstruct high-precision photoacoustic images. To obtain more accurate and clear image reconstruction results, PAI systems typically use a large number of ultrasound transducers to collect multi-channel signals from different angles and positions, thereby acquiring more information about the photoacoustic signals. Therefore, to reconstruct high-quality photoacoustic images, PAI systems require a significant number of measurement signals, which can result in substantial hardware and time costs. Compressed sensing is an algorithm that breaks through the Nyquist sampling theorem and can reconstruct the original signal with a small number of measurement signals. PAI based on compressed sensing has made breakthroughs over the past decade, enabling the reconstruction of low artifacts and high-quality images with a small number of photoacoustic measurement signals, improving time efficiency, and reducing hardware costs. This article provides a detailed introduction to PAI based on compressed sensing, such as the physical transmission model-based compressed sensing method, two-stage reconstruction-based compressed sensing method, and single-pixel camera-based compressed sensing method. Challenges and future perspectives of compressed sensing-based PAI are also discussed.

Advanced Imaging of Gout and Other Inflammatory Diseases Around the Knee.

The knee is one of the most commonly affected joints in the course of inflammatory arthropathies, such as crystal-induced and autoimmune inflammatory arthritis. The latter group includes systemic connective tissue diseases and spondyloarthropathies. The different pathogenesis of these entities results in their varied radiologic images. Some lead quickly to joint destruction, others only after many years, and in the remaining, destruction will not be a distinguishing radiologic feature.Radiography, ultrasonography, and magnetic resonance imaging have traditionally been the primary modalities in the diagnosis of noninflammatory and inflammatory arthropathies. In the case of crystallopathies, dual-energy computed tomography has been introduced. Hybrid techniques also offer new diagnostic opportunities. In this article, we discuss the pathologic findings and imaging correlations for crystallopathies and inflammatory diseases of the knee, with an emphasis on recent advances in their imaging diagnosis.

A novel deep learning technique for medical image analysis using improved optimizer.

Application of Convolutional neural network in spectrum of Medical image analysis are providing benchmark outputs which converges the interest of many researchers to explore it in depth. Latest preprocessing technique Real ESRGAN (Enhanced super resolution generative adversarial network) and GFPGAN (Generative facial prior GAN) are proving their efficacy in providing high resolution dataset. Objective: Optimizer plays a vital role in upgrading the functioning of CNN model. Different optimizers like Gradient descent, Stochastic Gradient descent, Adagrad, Adadelta and Adam etc. are used for classification and segmentation of Medical image but they suffer from slow processing due to their large memory requirement. Stochastic Gradient descent suffers from high variance and is computationally expensive. Dead neuron problem also proves to detrimental to the performance of most of the optimizers. A new optimization technique Gradient Centralization is providing the unparalleled result in terms of generalization and execution time. Method: Our paper explores the next factor which is the employment of new optimization technique, Gradient centralization (GC) to our integrated framework (Model with advanced preprocessing technique). Result and conclusion: Integrated Framework of Real ESRGAN and GFPGAN with Gradient centralization provides an optimal solution for deep learning models in terms of Execution time and Loss factor improvement.

Investigating the impact of data heterogeneity on the performance of federated learning algorithm using medical imaging.

In recent years, Federated Learning (FL) has gained traction as a privacy-centric approach in medical imaging. This study explores the challenges posed by data heterogeneity on FL algorithms, using the COVIDx CXR-3 dataset as a case study. We contrast the performance of the Federated Averaging (FedAvg) algorithm on non-identically and independently distributed (non-IID) data against identically and independently distributed (IID) data. Our findings reveal a notable performance decline with increased data heterogeneity, emphasizing the need for innovative strategies to enhance FL in diverse environments. This research contributes to the practical implementation of FL, extending beyond theoretical concepts and addressing the nuances in medical imaging applications. This research uncovers the inherent challenges in FL due to data diversity. It sets the stage for future advancements in FL strategies to effectively manage data heterogeneity, especially in sensitive fields like healthcare.

Non-gastrointestinal stromal tumor, mesenchymal neoplasms of the gastrointestinal tract: a review of tumor genetics, pathology, and cross-sectional imaging findings.

There is a diverse group of non-gastrointestinal stromal tumor (GIST), mesenchymal neoplasms of the gastrointestinal (GI) tract that demonstrate characteristic pathology and histogenesis as well as variable imaging findings and biological behavior. Recent advancements in tumor genetics have unveiled specific abnormalities associated with certain tumors, influencing their molecular pathogenesis, biology, response to treatment, and prognosis. Notably, giant fibrovascular polyps of the esophagus, identified through MDM2 gene amplifications, are now classified as liposarcomas. Some tumors exhibit distinctive patterns of disease distribution. Glomus tumors and plexiform fibromyxomas exhibit a pronounced affinity for the gastric antrum. In contrast, smooth muscle tumors within the GI tract are predominantly found in the esophagus and colorectum, surpassing the incidence of GISTs in these locations. Surgical resection suffices for symptomatic benign tumors; multimodality treatment may be necessary for frank sarcomas. This article aims to elucidate the cross-sectional imaging findings associated with a wide spectrum of these tumors, providing insights that align with their histopathological features.

Consumer electronics based smart technologies for enhanced terahertz healthcare having an integration of split learning with medical imaging.

The proposed work contains three major contribution, such as smart data collection, optimized training algorithm and integrating Bayesian approach with split learning to make privacy of the patent data. By integrating consumer electronics device such as wearable devices, and the Internet of Things (IoT) taking THz image, perform EM algorithm as training, used newly proposed slit learning method the technology promises enhanced imaging depth and improved tissue contrast, thereby enabling early and accurate disease detection the breast cancer disease. In our hybrid algorithm, the breast cancer model achieves an accuracy of 97.5 percent over 100 epochs, surpassing the less accurate old models which required a higher number of epochs, such as 165.

Imaging Assessment of Radiation Therapy-Related Normal Tissue Injury in Children: A PENTEC Visionary Statement.

The Pediatric Normal Tissue Effects in the Clinic (PENTEC) consortium has made significant contributions to understanding and mitigating the adverse effects of childhood cancer therapy. This review addresses the role of diagnostic imaging in detecting, screening, and comprehending radiation therapy-related late effects in children, drawing insights from individual organ-specific PENTEC reports. We further explore how the development of imaging biomarkers for key organ systems, alongside technical advancements and translational imaging approaches, may enhance the systematic application of imaging evaluations in childhood cancer survivors. Moreover, the review critically examines knowledge gaps and identifies technical and practical limitations of existing imaging modalities in the pediatric population. Addressing these challenges may expand access to, minimize the risk of, and optimize the real-world application of, new imaging techniques. The PENTEC team envisions this document as a roadmap for the future development of imaging strategies in childhood cancer survivors, with the overarching goal of improving long-term health outcomes and quality of life for this vulnerable population.

A comparative study of an on premise AutoML solution for medical image classification.

Automated machine learning (AutoML) allows for the simplified application of machine learning to real-world problems, by the implicit handling of necessary steps such as data pre-processing, feature engineering, model selection and hyperparameter optimization. This has encouraged its use in medical applications such as imaging. However, the impact of common parameter choices such as the number of trials allowed, and the resolution of the input images, has not been comprehensively explored in existing literature. We therefore benchmark AutoKeras (AK), an open-source AutoML framework, against several bespoke deep learning architectures, on five public medical datasets representing a wide range of imaging modalities. It was found that AK could outperform the bespoke models in general, although at the cost of increased training time. Moreover, our experiments suggest that a large number of trials and higher resolutions may not be necessary for optimal performance to be achieved.

AI-enhanced integration of genetic and medical imaging data for risk assessment of Type 2 diabetes.

Type 2 diabetes (T2D) presents a formidable global health challenge, highlighted by its escalating prevalence, underscoring the critical need for precision health strategies and early detection initiatives. Leveraging artificial intelligence, particularly eXtreme Gradient Boosting (XGBoost), we devise robust risk assessment models for T2D. Drawing upon comprehensive genetic and medical imaging datasets from 68,911 individuals in the Taiwan Biobank, our models integrate Polygenic Risk Scores (PRS), Multi-image Risk Scores (MRS), and demographic variables, such as age, sex, and T2D family history. Here, we show that our model achieves an Area Under the Receiver Operating Curve (AUC) of 0.94, effectively identifying high-risk T2D subgroups. A streamlined model featuring eight key variables also maintains a high AUC of 0.939. This high accuracy for T2D risk assessment promises to catalyze early detection and preventive strategies. Moreover, we introduce an accessible online risk assessment tool for T2D, facilitating broader applicability and dissemination of our findings.

Neurogenic thoracic outlet syndrome and controversies in diagnosis and management.

Compression of the neurovascular structures at the level of the scalene triangle and pectoralis minor space is rare, but increasing awareness and understanding is allowing for the treatment of more individuals than in the past. We outlined the recognition, preoperative evaluation, and treatment of patients with neurogenic thoracic outlet syndrome. Recent work has illustrated the role of imaging and centrality of the physical examination on the diagnosis. However, a fuller understanding of the spatial biomechanics of the shoulder, scalene triangle, and pectoralis minor musculotendinous complex has shown that, although physical therapy is a mainstay of treatment, a poor response to physical therapy with a sound diagnosis should not preclude decompression. Modes of failure of surgical decompression stress the importance of full resection of the anterior scalene muscle and all posterior rib impinging elements to minimize the risk of recurrence of symptoms. Neurogenic thoracic outlet syndrome is a rare but critical cause of disability of the upper extremity. Modern understanding of the pathophysiology and evaluation have led to a sounder diagnosis. Although physical therapy is a mainstay, surgical decompression remains the gold standard to preserve and recover function of the upper extremity. Understanding these principles will be central to further developments in the treatment of this patient population.

Current concepts in clinical features and diagnosis of thoracic outlet syndrome.

The diagnosis and clinical features of thoracic outlet syndrome have long confounded clinicians, owing to heterogeneity in symptom presentation and many overlapping competing diagnoses that are "more common." Despite the advent and prevalence of high-resolution imaging, along with the increasing awareness of the syndrome itself, misdiagnoses and untimely diagnoses can result in significant patient morbidity. The authors aimed to summarize the current concepts in the clinical features and diagnosis of thoracic outlet syndrome.

Surface engineered nanodiamonds: mechanistic intervention in biomedical applications for diagnosis and treatment of cancer.

In terms of biomedical tools, nanodiamonds (ND) are a more recent innovation. Their size typically ranges between 4 to 100 nm. ND are produced via a variety of methods and are known for their physical toughness, durability, and chemical stability. Studies have revealed that surface modifications and functionalization have a significant influence on the optical and electrical properties of the nanomaterial. Consequently, surface functional groups of NDs have applications in a variety of domains, including drug administration, gene delivery, immunotherapy for cancer treatment, and bio-imaging to diagnose cancer. Additionally, their biocompatibility is a critical requisite for theirin vivoandin vitrointerventions. This review delves into these aspects and focuses on the recent advances in surface modification strategies of NDs for various biomedical applications surrounding cancer diagnosis and treatment. Furthermore, the prognosis of its clinical translation has also been discussed.

Vascular compression syndromes in the abdomen and pelvis: a concise pictorial review.

Vascular compression syndromes are a diverse group of pathologies that can manifest asymptomatically and incidentally in otherwise healthy individuals or symptomatically with a spectrum of presentations. Due to their relative rarity, these syndromes are often poorly understood and overlooked. Early identification of these syndromes can have a significant impact on subsequent clinical management. This pictorial review provides a concise summary of seven vascular compression syndromes within the abdomen and pelvis including median arcuate ligament (MAL) syndrome, superior mesenteric artery (SMA) syndrome, nutcracker syndrome (NCS), May-Thurner syndrome (MTS), ureteropelvic junction obstruction (UPJO), vascular compression of the ureter, and portal biliopathy. The demographics, pathophysiology, predisposing factors, and expected treatment for each compression syndrome are reviewed. Salient imaging features of each entity are illustrated through imaging examples using multiple modalities including ultrasound, fluoroscopy, CT, and MRI.

[Imaging in headache]. / Bildgebung bei Kopfschmerzen.

Headache is worldwide one of the leading reasons to consult a general practitioner or a neurologist. In addition to the medical history and results of laboratory parameters, imaging represents one of the most important diagnostic steps. As there is a myriad of possible causes, it is nearly impossible to cover the whole spectrum of this topic. This article summarizes the most important morphological imaging findings and their pitfalls.

Vision, body and interpretation in medical imaging diagnostics.

This article explores the profound impact of visualism and visual perception in the context of medical imaging diagnostics. It emphasizes the intricate interplay among vision, embodiment, subjectivity, language, and historicity within the realm of medical science and technology, with a specific focus on image consciousness. The study delves into the role of subjectivity in perception, facilitating the communication of opacity and historicity to the perceiving individual. Additionally, it scrutinizes the image interpretation process, drawing parallels to text interpretation and highlighting the influence of personal biases and individuality in medical practice. By revisiting Husserl's conceptualization of "image consciousness" and introducing the notion of "image theme", the paper seeks to establish a theoretical framework for making sense of images within the context of technological interpretation. A key objective is to enhance the phenomenology of technology through a systematic analysis of medical imaging diagnosis, contributing to an expanded epistemological foundation for medical practice. The article recognizes that the construction of medical knowledge incorporates subjective elements, especially within a historical context. The interpretation of images involves both instrumental and expert interpretation, with human subjectivity playing a crucial role. The article asserts that human creativity and conscious engagement are indispensable in interpreting all medical images.

[Medical image segmentation data augmentation method based on channel weight and data-efficient features].

In computer-aided medical diagnosis, obtaining labeled medical image data is expensive, while there is a high demand for model interpretability. However, most deep learning models currently require a large amount of data and lack interpretability. To address these challenges, this paper proposes a novel data augmentation method for medical image segmentation. The uniqueness and advantages of this method lie in the utilization of gradient-weighted class activation mapping to extract data efficient features, which are then fused with the original image. Subsequently, a new channel weight feature extractor is constructed to learn the weights between different channels. This approach achieves non-destructive data augmentation effects, enhancing the model's performance, data efficiency, and interpretability. Applying the method of this paper to the Hyper-Kvasir dataset, the intersection over union (IoU) and Dice of the U-net were improved, respectively; and on the ISIC-Archive dataset, the IoU and Dice of the DeepLabV3+ were also improved respectively. Furthermore, even when the training data is reduced to 70 %, the proposed method can still achieve performance that is 95 % of that achieved with the entire dataset, indicating its good data efficiency. Moreover, the data-efficient features used in the method have interpretable information built-in, which enhances the interpretability of the model. The method has excellent universality, is plug-and-play, applicable to various segmentation methods, and does not require modification of the network structure, thus it is easy to integrate into existing medical image segmentation method, enhancing the convenience of future research and applications.