Deep generative models and synthetic medical data have shown significant promise in addressing key challenges in healthcare, such as privacy concerns, data bias, and the scarcity of realistic datasets. While research in this area has grown rapidly and demonstrated substantial theoretical potential, its practical adoption in clinical settings remains limited. Despite the benefits synthetic data offers, questions surrounding its reliability and credibility persist, leading to a lack of trust among clinicians. This position paper argues that fostering trust in synthetic medical data is crucial for its clinical adoption. It aims to spark a discussion on the viability of synthetic medical data in clinical practice, particularly in the context of current advancements in AI. We present empirical evidence from brain tumor segmentation to demonstrate that the quality, diversity, and proportion of synthetic data directly impact trust in clinical AI models. Our findings provide insights to improve the deployment and acceptance of synthetic data-driven AI systems in real-world clinical workflows.

The updated recommendations on diagnostic procedures and treatment pathways for a medical condition are documented as graphical flows in Clinical Practice Guidelines (CPGs). For effective use of the CPGs in helping medical professionals in the treatment decision process, it is necessary to fully capture the guideline knowledge, particularly the contexts and their relationships in the graph. While several existing works have utilized these guidelines to create rule bases for Clinical Decision Support Systems, limited work has been done toward directly capturing the full medical knowledge contained in CPGs. This work proposes an approach to create a contextually enriched, faithful digital representation of National Comprehensive Cancer Network (NCCN) Cancer CPGs in the form of graphs using automated extraction and node & relationship classification. We also implement semantic enrichment of the model by using Large Language Models (LLMs) for node classification, achieving an accuracy of 80.86% and 88.47% with zero-shot learning and few-shot learning, respectively. Additionally, we introduce a methodology for answering natural language questions with constraints to guideline text by leveraging LLMs to extract the relevant subgraph from the guideline knowledge base. By generating natural language answers based on subgraph paths and semantic information, we mitigate the risk of incorrect answers and hallucination associated with LLMs, ensuring factual accuracy in medical domain Question Answering.

In response to the growing demand for precise and affordable solutions for Image-Guided Spine Surgery (IGSS), this paper presents a comprehensive development of a Robot-Assisted and Navigation-Guided IGSS System. The endeavor involves integrating cutting-edge technologies to attain the required surgical precision and limit user radiation exposure, thereby addressing the limitations of manual surgical methods. We propose an IGSS workflow and system architecture employing a hybrid-layered approach, combining modular and integrated system architectures in distinctive layers to develop an affordable system for seamless integration, scalability, and reconfigurability. We developed and integrated the system and extensively tested it on phantoms and cadavers. The proposed system's accuracy using navigation guidance is 1.020 mm, and robot assistance is 1.11 mm on phantoms. Observing a similar performance in cadaveric validation where 84% of screw placements were grade A, 10% were grade B using navigation guidance, 90% were grade A, and 10% were grade B using robot assistance as per the Gertzbein-Robbins scale, proving its efficacy for an IGSS. The evaluated performance is adequate for an IGSS and at par with the existing systems in literature and those commercially available. The user radiation is lower than in the literature, given that the system requires only an average of 3 C-Arm images per pedicle screw placement and verification

Maternal health remains a pervasive challenge in developing and underdeveloped countries. Inadequate access to basic antenatal Ultrasound (US) examinations, limited resources such as primary health services and infrastructure, and lack of skilled healthcare professionals are the major concerns. To improve the quality of maternal care, robot-assisted antenatal US systems with teleoperable and autonomous capabilities were introduced. However, the existing teleoperation systems rely on standard video stream-based approaches that are constrained by limited immersion and scene awareness. Also, there is no prior work on autonomous antenatal robotic US systems that automate standardized scanning protocols. To that end, this paper introduces a novel Virtual Reality (VR) platform for robotic antenatal ultrasound, which enables sonologists to control a robotic arm over a wired network. The effectiveness of the system is enhanced by providing a reconstructed 3D view of the environment and immersing the user in a VR space. Also, the system facilitates a better understanding of the anatomical surfaces to perform pragmatic scans using 3D models. Further, the proposed robotic system also has autonomous capabilities; under the supervision of the sonologist, it can perform the standard six-step approach for obstetric US scanning recommended by the ISUOG. Using a 23-week fetal phantom, the proposed system was demonstrated to technology and academia experts at MEDICA 2022 as a part of the KUKA Innovation Award. The positive feedback from them supports the feasibility of the system. It also gave an insight into the improvisations to be carried out to make it a clinically viable system.

Transformers have emerged as viable alternatives to convolutional neural networks owing to their ability to learn non-local region relationships in the spatial domain. The self-attention mechanism of the transformer enables transformers to capture long-range dependencies in the images, which might be desirable for accelerated MRI image reconstruction as the effect of undersampling is non-local in the image domain. Despite its computational efficiency, the window-based transformers suffer from restricted receptive fields as the dependencies are limited to within the scope of the image windows. We propose a window-based transformer network that integrates dilated attention mechanism and convolution for accelerated MRI image reconstruction. The proposed network consists of dilated and dense neighborhood attention transformers to enhance the distant neighborhood pixel relationship and introduce depth-wise convolutions within the transformer module to learn low-level translation invariant features for accelerated MRI image reconstruction. The proposed model is trained in a self-supervised manner. We perform extensive experiments for multi-coil MRI acceleration for coronal PD, coronal PDFS and axial T2 contrasts with 4x and 5x under-sampling in self-supervised learning based on k-space splitting. We compare our method against other reconstruction architectures and the parallel domain self-supervised learning baseline. Results show that the proposed model exhibits improvement margins of (i) around 1.40 dB in PSNR and around 0.028 in SSIM on average over other architectures (ii) around 1.44 dB in PSNR and around 0.029 in SSIM over parallel domain self-supervised learning. The code is available at https://github.com/rahul-gs-16/sdlformer.git

Clinical Practice Guidelines (CPGs) for cancer diseases evolve rapidly due to new evidence generated by active research. Currently, CPGs are primarily published in a document format that is ill-suited for managing this developing knowledge. A knowledge model of the guidelines document suitable for programmatic interaction is required. This work proposes an automated method for extraction of knowledge from National Comprehensive Cancer Network (NCCN) CPGs in Oncology and generating a structured model containing the retrieved knowledge. The proposed method was tested using two versions of NCCN Non-Small Cell Lung Cancer (NSCLC) CPG to demonstrate the effectiveness in faithful extraction and modeling of knowledge. Three enrichment strategies using Cancer staging information, Unified Medical Language System (UMLS) Metathesaurus & National Cancer Institute thesaurus (NCIt) concepts, and Node classification are also presented to enhance the model towards enabling programmatic traversal and querying of cancer care guidelines. The Node classification was performed using a Support Vector Machine (SVM) model, achieving a classification accuracy of 0.81 with 10-fold cross-validation.

Meta-learning has recently been an emerging data-efficient learning technique for various medical imaging operations and has helped advance contemporary deep learning models. Furthermore, meta-learning enhances the knowledge generalization of the imaging tasks by learning both shared and discriminative weights for various configurations of imaging tasks. However, existing meta-learning models attempt to learn a single set of weight initializations of a neural network that might be restrictive for multimodal data. This work aims to develop a multimodal meta-learning model for image reconstruction, which augments meta-learning with evolutionary capabilities to encompass diverse acquisition settings of multimodal data. Our proposed model called KM-MAML (Kernel Modulation-based Multimodal Meta-Learning), has hypernetworks that evolve to generate mode-specific weights. These weights provide the mode-specific inductive bias for multiple modes by re-calibrating each kernel of the base network for image reconstruction via a low-rank kernel modulation operation. We incorporate gradient-based meta-learning (GBML) in the contextual space to update the weights of the hypernetworks for different modes. The hypernetworks and the reconstruction network in the GBML setting provide discriminative mode-specific features and low-level image features, respectively. Experiments on multi-contrast MRI reconstruction show that our model, (i) exhibits superior reconstruction performance over joint training, other meta-learning methods, and context-specific MRI reconstruction methods, and (ii) better adaptation capabilities with improvement margins of 0.5 dB in PSNR and 0.01 in SSIM. Besides, a representation analysis with U-Net shows that kernel modulation infuses 80% of mode-specific representation changes in the high-resolution layers. Our source code is available at https://github.com/sriprabhar/KM-MAML/.

Deep cascaded architectures for magnetic resonance imaging (MRI) acceleration have shown remarkable success in providing high-quality reconstruction. However, as the number of cascades increases, the improvements in reconstruction tend to become marginal, indicating possible excess model capacity. Knowledge distillation (KD) is an emerging technique to compress these models, in which a trained deep teacher network is used to distill knowledge to a smaller student network such that the student learns to mimic the behavior of the teacher. Most KD methods focus on effectively training the student with a pre-trained teacher unaware of the student model. We propose SFT-KD-Recon, a student-friendly teacher training approach along with the student as a prior step to KD to make the teacher aware of the structure and capacity of the student and enable aligning the representations of the teacher with the student. In SFT, the teacher is jointly trained with the unfolded branch configurations of the student blocks using three loss terms - teacher-reconstruction loss, student-reconstruction loss, and teacher-student imitation loss, followed by KD of the student. We perform extensive experiments for MRI acceleration in 4x and 5x under-sampling on the brain and cardiac datasets on five KD methods using the proposed approach as a prior step. We consider the DC-CNN architecture and setup teacher as D5C5 (141765 parameters), and student as D3C5 (49285 parameters), denoting a compression of 2.87:1. Results show that (i) our approach consistently improves the KD methods with improved reconstruction performance and image quality, and (ii) the student distilled using our approach is competitive with the teacher, with the performance gap reduced from 0.53 dB to 0.03 dB.

An electroencephalogram (EEG) signal is currently accepted as a standard for automatic sleep staging. Lately, Near-human accuracy in automated sleep staging has been achievable by Deep Learning (DL) based approaches, enabling multi-fold progress in this area. However, An extensive and expensive clinical setup is required for EEG based sleep staging. Additionally, the EEG setup being obtrusive in nature and requiring an expert for setup adds to the inconvenience of the subject under study, making it adverse in the point of care setting. An unobtrusive and more suitable alternative to EEG is Electrocardiogram (ECG). Unsurprisingly, compared to EEG in sleep staging, its performance remains sub-par. In order to take advantage of both the modalities, transferring knowledge from EEG to ECG is a reasonable approach, ultimately boosting the performance of ECG based sleep staging. Knowledge Distillation (KD) is a promising notion in DL that shares knowledge from a superior performing but usually more complex teacher model to an inferior but compact student model. Building upon this concept, a cross-modality KD framework assisting features learned through models trained on EEG to improve ECG-based sleep staging performance is proposed. Additionally, to better understand the distillation approach, extensive experimentation on the independent modules of the proposed model was conducted. Montreal Archive of Sleep Studies (MASS) dataset consisting of 200 subjects was utilized for this study. The results from the proposed model for weighted-F1-score in 3-class and 4-class sleep staging showed a 13.40 \% and 14.30 \% improvement, respectively. This study demonstrates the feasibility of KD for single-channel ECG based sleep staging's performance enhancement in 3-class (W-R-N) and 4-class (W-R-L-D) classification.

Automatic Sleep Staging study is presently done with the help of Electroencephalogram (EEG) signals. Recently, Deep Learning (DL) based approaches have enabled significant progress in this area, allowing for near-human accuracy in automated sleep staging. However, EEG based sleep staging requires an extensive as well as an expensive clinical setup. Moreover, the requirement of an expert for setup and the added inconvenience to the subject under study renders it unfavourable in a point of care context. Electrocardiogram (ECG), an unobtrusive alternative to EEG, is more suitable, but its performance, unsurprisingly, remains sub-par compared to EEG-based sleep staging. Naturally, it would be helpful to transfer knowledge from EEG to ECG, ultimately enhancing the model's performance on ECG based inputs. Knowledge Distillation (KD) is a renowned concept in DL that looks to transfer knowledge from a better but potentially more cumbersome teacher model to a compact student model. Building on this concept, we propose a cross-modal KD framework to improve ECG-based sleep staging performance with assistance from features learned through models trained on EEG. Additionally, we also conducted multiple experiments on the individual components of the proposed model to get better insight into the distillation approach. Data of 200 subjects from the Montreal Archive of Sleep Studies (MASS) was utilized for our study. The proposed model showed a 14.3\% and 13.4\% increase in weighted-F1-score in 4-class and 3-class sleep staging, respectively. This demonstrates the viability of KD for performance improvement of single-channel ECG based sleep staging in 4-class(W-L-D-R) and 3-class(W-N-R) classification.