arXiv subjects

Ghulam Rasool

Publications and source records attributed to Ghulam Rasool.

At least 19 recordsLinked to original sources

arXiv2026

Multi-Agent AI System for Radiology Report Structuring and Quality Assurance with Independent Radiologist Evaluation

Purpose: To develop and evaluate a locally deployed multi-agent AI system for radiology report structuring and quality assurance. Materials and Methods: This retrospective study included 638 radiology reports from CT examinations of the chest, abdomen, and pelvis dictated by 15 board-certified radiologists in 2023 and 2024. A multi-agent AI pipeline was developed to perform report structuring and quality assurance (QA). The system structured the report into standardized anatomical sections at the sentence level using regex rules and local large language models. It also detected mismatches between the Findings and Impression sections, or within sections; gender-anatomy conflicts; and undocumented communication of critical findings. Two board-certified radiologists independently evaluated a 45-report subset. Results: The multi-agent system structured the Findings sections of all reports (22,270 sentences) into a predefined anatomical format while retaining the original report content. The system flagged 90 (14.1%) reports, most commonly for section mismatches (80 reports, 12.5%). In the radiologist evaluation, both reviewers agreed that 31 (69%) were correctly restructured, 2 reports (4%) were incorrectly restructured, and disagreed on the remaining 12 reports (27%). Both reviewers agreed that no clinically important information was omitted and no fabricated content was introduced. Overall QA performance was rated as "excellent" or "good" in 84% of the evaluated reports, with the remaining reports rated as "fair". Conclusion: A locally deployed multi-agent AI system combined radiology report structuring and quality assurance within a single workflow. The system demonstrated favorable performance in radiologist evaluation. Such systems may support standardization of reporting and quality assurance in radiology practice.

cs.CL↗

arXiv2025

Medical Image De-Identification Benchmark Challenge

The de-identification (deID) of protected health information (PHI) and personally identifiable information (PII) is a fundamental requirement for sharing medical images, particularly through public repositories, to ensure compliance with patient privacy laws. In addition, preservation of non-PHI metadata to inform and enable downstream development of imaging artificial intelligence (AI) is an important consideration in biomedical research. The goal of MIDI-B was to provide a standardized platform for benchmarking of DICOM image deID tools based on a set of rules conformant to the HIPAA Safe Harbor regulation, the DICOM Attribute Confidentiality Profiles, and best practices in preservation of research-critical metadata, as defined by The Cancer Imaging Archive (TCIA). The challenge employed a large, diverse, multi-center, and multi-modality set of real de-identified radiology images with synthetic PHI/PII inserted. The MIDI-B Challenge consisted of three phases: training, validation, and test. Eighty individuals registered for the challenge. In the training phase, we encouraged participants to tune their algorithms using their in-house or public data. The validation and test phases utilized the DICOM images containing synthetic identifiers (of 216 and 322 subjects, respectively). Ten teams successfully completed the test phase of the challenge. To measure success of a rule-based approach to image deID, scores were computed as the percentage of correct actions from the total number of required actions. The scores ranged from 97.91% to 99.93%. Participants employed a variety of open-source and proprietary tools with customized configurations, large language models, and optical character recognition (OCR). In this paper we provide a comprehensive report on the MIDI-B Challenge's design, implementation, results, and lessons learned.

cs.CV↗

arXiv2025

DICOM De-Identification via Hybrid AI and Rule-Based Framework for Scalable, Uncertainty-Aware Redaction

Access to medical imaging and associated text data has the potential to drive major advances in healthcare research and patient outcomes. However, the presence of Protected Health Information (PHI) and Personally Identifiable Information (PII) in Digital Imaging and Communications in Medicine (DICOM) files presents a significant barrier to the ethical and secure sharing of imaging datasets. This paper presents a hybrid de-identification framework developed by Impact Business Information Solutions (IBIS) that combines rule-based and AI-driven techniques, and rigorous uncertainty quantification for comprehensive PHI/PII removal from both metadata and pixel data. Our approach begins with a two-tiered rule-based system targeting explicit and inferred metadata elements, further augmented by a large language model (LLM) fine-tuned for Named Entity Recognition (NER), and trained on a suite of synthetic datasets simulating realistic clinical PHI/PII. For pixel data, we employ an uncertainty-aware Faster R-CNN model to localize embedded text, extract candidate PHI via Optical Character Recognition (OCR), and apply the NER pipeline for final redaction. Crucially, uncertainty quantification provides confidence measures for AI-based detections to enhance automation reliability and enable informed human-in-the-loop verification to manage residual risks. This uncertainty-aware deidentification framework achieves robust performance across benchmark datasets and regulatory standards, including DICOM, HIPAA, and TCIA compliance metrics. By combining scalable automation, uncertainty quantification, and rigorous quality assurance, our solution addresses critical challenges in medical data de-identification and supports the secure, ethical, and trustworthy release of imaging data for research.

stat.ML↗

arXiv2025

Explainable AI in Genomics: Transcription Factor Binding Site Prediction with Mixture of Experts

Transcription Factor Binding Site (TFBS) prediction is crucial for understanding gene regulation and various biological processes. This study introduces a novel Mixture of Experts (MoE) approach for TFBS prediction, integrating multiple pre-trained Convolutional Neural Network (CNN) models, each specializing in different TFBS patterns. We evaluate the performance of our MoE model against individual expert models on both in-distribution and out-of-distribution (OOD) datasets, using six randomly selected transcription factors (TFs) for OOD testing. Our results demonstrate that the MoE model achieves competitive or superior performance across diverse TF binding sites, particularly excelling in OOD scenarios. The Analysis of Variance (ANOVA) statistical test confirms the significance of these performance differences. Additionally, we introduce ShiftSmooth, a novel attribution mapping technique that provides more robust model interpretability by considering small shifts in input sequences. Through comprehensive explainability analysis, we show that ShiftSmooth offers superior attribution for motif discovery and localization compared to traditional Vanilla Gradient methods. Our work presents an efficient, generalizable, and interpretable solution for TFBS prediction, potentially enabling new discoveries in genome biology and advancing our understanding of transcriptional regulation.

cs.LG↗

arXiv2025

EAGLE: Efficient Alignment of Generalized Latent Embeddings for Multimodal Survival Prediction with Interpretable Attribution Analysis

Accurate cancer survival prediction requires integration of diverse data modalities that reflect the complex interplay between imaging, clinical parameters, and textual reports. However, existing multimodal approaches suffer from simplistic fusion strategies, massive computational requirements, and lack of interpretability-critical barriers to clinical adoption. We present EAGLE (Efficient Alignment of Generalized Latent Embeddings), a novel deep learning framework that addresses these limitations through attention-based multimodal fusion with comprehensive attribution analysis. EAGLE introduces four key innovations: (1) dynamic cross-modal attention mechanisms that learn hierarchical relationships between modalities, (2) massive dimensionality reduction (99.96%) while maintaining predictive performance, (3) three complementary attribution methods providing patient-level interpretability, and (4) a unified pipeline enabling seamless adaptation across cancer types. We evaluated EAGLE on 911 patients across three distinct malignancies: glioblastoma (GBM, n=160), intraductal papillary mucinous neoplasms (IPMN, n=171), and non-small cell lung cancer (NSCLC, n=580). Patient-level analysis showed high-risk individuals relied more heavily on adverse imaging features, while low-risk patients demonstrated balanced modality contributions. Risk stratification identified clinically meaningful groups with 4-fold (GBM) to 5-fold (NSCLC) differences in median survival, directly informing treatment intensity decisions. By combining state-of-the-art performance with clinical interpretability, EAGLE bridges the gap between advanced AI capabilities and practical healthcare deployment, offering a scalable solution for multimodal survival prediction that enhances both prognostic accuracy and physician trust in automated predictions.

cs.LG↗

arXiv2025

Trustworthy AI for Medicine: Continuous Hallucination Detection and Elimination with CHECK

Large language models (LLMs) show promise in healthcare, but hallucinations remain a major barrier to clinical use. We present CHECK, a continuous-learning framework that integrates structured clinical databases with a classifier grounded in information theory to detect both factual and reasoning-based hallucinations. Evaluated on 1500 questions from 100 pivotal clinical trials, CHECK reduced LLama3.3-70B-Instruct hallucination rates from 31% to 0.3% - making an open source model state of the art. Its classifier generalized across medical benchmarks, achieving AUCs of 0.95-0.96, including on the MedQA (USMLE) benchmark and HealthBench realistic multi-turn medical questioning. By leveraging hallucination probabilities to guide GPT-4o's refinement and judiciously escalate compute, CHECK boosted its USMLE passing rate by 5 percentage points, achieving a state-of-the-art 92.1%. By suppressing hallucinations below accepted clinical error thresholds, CHECK offers a scalable foundation for safe LLM deployment in medicine and other high-stakes domains.

cs.CL↗

arXiv2025

TheBlueScrubs-v1, a comprehensive curated medical dataset derived from the internet

The need for robust and diverse data sets to train clinical large language models (cLLMs) is critical given that currently available public repositories often prove too limited in size or scope for comprehensive medical use. While resources like PubMed provide foundational medical literature, they capture only a narrow range of formal publications and omit the broader medical discourse on the internet. To address these deficits, we introduce TheBlueScrubs-v1, a curated dataset of over 25 billion medical tokens - nearly three times larger than PubMed - drawn from a broad-scale internet corpus. Our two-stage filtering pipeline employs a Logistic Regression model for document screening (achieving an AUC of approximately 0.95 on external validation), followed by verification via a 70B-parameter Llama 3.1 instruct model. Each text is assigned three LLM-based quality scores encompassing medical relevance, precision and factual detail, and safety and ethical standards. Clinician reviews confirm high concordance with these automated evaluations, and a specialized cancer classifier further labels approximately 11 billion oncology tokens. Two demonstration tasks highlight the dataset's practical value: first, we distill the safety evaluations to a smaller BERT-style model that reaches an AUC near 0.96 on unseen data; second, we fine-tune a compact LLM on a filtered subset, showing measurable improvements over standard baselines in medical benchmarks as well as private ones. This Data Descriptor details the dataset's creation and validation, underscoring its potential utility for medical AI research.

cs.CL↗

arXiv2025

Reliable Radiologic Skeletal Muscle Area Assessment -- A Biomarker for Cancer Cachexia Diagnosis

Cancer cachexia is a common metabolic disorder characterized by severe muscle atrophy which is associated with poor prognosis and quality of life. Monitoring skeletal muscle area (SMA) longitudinally through computed tomography (CT) scans, an imaging modality routinely acquired in cancer care, is an effective way to identify and track this condition. However, existing tools often lack full automation and exhibit inconsistent accuracy, limiting their potential for integration into clinical workflows. To address these challenges, we developed SMAART-AI (Skeletal Muscle Assessment-Automated and Reliable Tool-based on AI), an end-to-end automated pipeline powered by deep learning models (nnU-Net 2D) trained on mid-third lumbar level CT images with 5-fold cross-validation, ensuring generalizability and robustness. SMAART-AI incorporates an uncertainty-based mechanism to flag high-error SMA predictions for expert review, enhancing reliability. We combined the SMA, skeletal muscle index, BMI, and clinical data to train a multi-layer perceptron (MLP) model designed to predict cachexia at the time of cancer diagnosis. Tested on the gastroesophageal cancer dataset, SMAART-AI achieved a Dice score of 97.80% +/- 0.93%, with SMA estimated across all four datasets in this study at a median absolute error of 2.48% compared to manual annotations with SliceOmatic. Uncertainty metrics-variance, entropy, and coefficient of variation-strongly correlated with SMA prediction errors (0.83, 0.76, and 0.73 respectively). The MLP model predicts cachexia with 79% precision, providing clinicians with a reliable tool for early diagnosis and intervention. By combining automation, accuracy, and uncertainty awareness, SMAART-AI bridges the gap between research and clinical application, offering a transformative approach to managing cancer cachexia.

eess.IV↗

arXiv2025

Multimodal AI-driven Biomarker for Early Detection of Cancer Cachexia

Cancer cachexia is a multifactorial syndrome characterized by progressive muscle wasting, metabolic dysfunction, and systemic inflammation, leading to reduced quality of life and increased mortality. Despite extensive research, no single definitive biomarker exists, as cachexia-related indicators such as serum biomarkers, skeletal muscle measurements, and metabolic abnormalities often overlap with other conditions. Existing composite indices, including the Cancer Cachexia Index (CXI), Modified CXI (mCXI), and Cachexia Score (CASCO), integrate multiple biomarkers but lack standardized thresholds, limiting their clinical utility. This study proposes a multimodal AI-based biomarker for early cancer cachexia detection, leveraging open-source large language models (LLMs) and foundation models trained on medical data. The approach integrates heterogeneous patient data, including demographics, disease status, lab reports, radiological imaging (CT scans), and clinical notes, using a machine learning framework that can handle missing data. Unlike previous AI-based models trained on curated datasets, this method utilizes routinely collected clinical data, enhancing real-world applicability. Additionally, the model incorporates confidence estimation, allowing the identification of cases requiring expert review for precise clinical interpretation. Preliminary findings demonstrate that integrating multiple data modalities improves cachexia prediction accuracy at the time of cancer diagnosis. The AI-based biomarker dynamically adapts to patient-specific factors such as age, race, ethnicity, weight, cancer type, and stage, avoiding the limitations of fixed-threshold biomarkers. This multimodal AI biomarker provides a scalable and clinically viable solution for early cancer cachexia detection, facilitating personalized interventions and potentially improving treatment outcomes and patient survival.

eess.IV↗

arXiv2024

Improving Radiology Report Conciseness and Structure via Local Large Language Models

Radiology reports are often lengthy and unstructured, posing challenges for referring physicians to quickly identify critical imaging findings while increasing the risk of missed information. This retrospective study aimed to enhance radiology reports by making them concise and well-structured, with findings organized by relevant organs. To achieve this, we utilized private large language models (LLMs) deployed locally within our institution's firewall, ensuring data security and minimizing computational costs. Using a dataset of 814 radiology reports from seven board-certified body radiologists at Moffitt Cancer Center, we tested five prompting strategies within the LangChain framework. After evaluating several models, the Mixtral LLM demonstrated superior adherence to formatting requirements compared to alternatives like Llama. The optimal strategy involved condensing reports first and then applying structured formatting based on specific instructions, reducing verbosity while improving clarity. Across all radiologists and reports, the Mixtral LLM reduced redundant word counts by more than 53%. These findings highlight the potential of locally deployed, open-source LLMs to streamline radiology reporting. By generating concise, well-structured reports, these models enhance information retrieval and better meet the needs of referring physicians, ultimately improving clinical workflows.

cs.CL↗

arXiv2024

Future-Proofing Medical Imaging with Privacy-Preserving Federated Learning and Uncertainty Quantification: A Review

Artificial Intelligence (AI) has demonstrated significant potential in automating various medical imaging tasks, which could soon become routine in clinical practice for disease diagnosis, prognosis, treatment planning, and post-treatment surveillance. However, the privacy concerns surrounding patient data present a major barrier to the widespread adoption of AI in medical imaging, as large, diverse training datasets are essential for developing accurate, generalizable, and robust Artificial intelligence models. Federated Learning (FL) offers a solution that enables organizations to train AI models collaboratively without sharing sensitive data. federated learning exchanges model training information, such as gradients, between the participating sites. Despite its promise, federated learning is still in its developmental stages and faces several challenges. Notably, sensitive information can still be inferred from the gradients shared during model training. Quantifying AI models' uncertainty is vital due to potential data distribution shifts post-deployment, which can affect model performance. Uncertainty quantification (UQ) in FL is particularly challenging due to data heterogeneity across participating sites. This review provides a comprehensive examination of FL, privacy-preserving FL (PPFL), and UQ in FL. We identify key gaps in current FL methodologies and propose future research directions to enhance data privacy and trustworthiness in medical imaging applications.

eess.IV↗

arXiv2024

Privacy Preserving Federated Learning in Medical Imaging with Uncertainty Estimation

Machine learning (ML) and Artificial Intelligence (AI) have fueled remarkable advancements, particularly in healthcare. Within medical imaging, ML models hold the promise of improving disease diagnoses, treatment planning, and post-treatment monitoring. Various computer vision tasks like image classification, object detection, and image segmentation are poised to become routine in clinical analysis. However, privacy concerns surrounding patient data hinder the assembly of large training datasets needed for developing and training accurate, robust, and generalizable models. Federated Learning (FL) emerges as a compelling solution, enabling organizations to collaborate on ML model training by sharing model training information (gradients) rather than data (e.g., medical images). FL's distributed learning framework facilitates inter-institutional collaboration while preserving patient privacy. However, FL, while robust in privacy preservation, faces several challenges. Sensitive information can still be gleaned from shared gradients that are passed on between organizations during model training. Additionally, in medical imaging, quantifying model confidence\uncertainty accurately is crucial due to the noise and artifacts present in the data. Uncertainty estimation in FL encounters unique hurdles due to data heterogeneity across organizations. This paper offers a comprehensive review of FL, privacy preservation, and uncertainty estimation, with a focus on medical imaging. Alongside a survey of current research, we identify gaps in the field and suggest future directions for FL research to enhance privacy and address noisy medical imaging data challenges.

cs.LG↗

arXiv2024

Embedding-based Multimodal Learning on Pan-Squamous Cell Carcinomas for Improved Survival Outcomes

Cancer clinics capture disease data at various scales, from genetic to organ level. Current bioinformatic methods struggle to handle the heterogeneous nature of this data, especially with missing modalities. We propose PARADIGM, a Graph Neural Network (GNN) framework that learns from multimodal, heterogeneous datasets to improve clinical outcome prediction. PARADIGM generates embeddings from multi-resolution data using foundation models, aggregates them into patient-level representations, fuses them into a unified graph, and enhances performance for tasks like survival analysis. We train GNNs on pan-Squamous Cell Carcinomas and validate our approach on Moffitt Cancer Center lung SCC data. Multimodal GNN outperforms other models in patient survival prediction. Converging individual data modalities across varying scales provides a more insightful disease view. Our solution aims to understand the patient's circumstances comprehensively, offering insights on heterogeneous data integration and the benefits of converging maximum data views.

q-bio.CB↗

arXiv2024

Adversarially Diversified Rehearsal Memory (ADRM): Mitigating Memory Overfitting Challenge in Continual Learning

Continual learning focuses on learning non-stationary data distribution without forgetting previous knowledge. Rehearsal-based approaches are commonly used to combat catastrophic forgetting. However, these approaches suffer from a problem called "rehearsal memory overfitting, " where the model becomes too specialized on limited memory samples and loses its ability to generalize effectively. As a result, the effectiveness of the rehearsal memory progressively decays, ultimately resulting in catastrophic forgetting of the learned tasks. We introduce the Adversarially Diversified Rehearsal Memory (ADRM) to address the memory overfitting challenge. This novel method is designed to enrich memory sample diversity and bolster resistance against natural and adversarial noise disruptions. ADRM employs the FGSM attacks to introduce adversarially modified memory samples, achieving two primary objectives: enhancing memory diversity and fostering a robust response to continual feature drifts in memory samples. Our contributions are as follows: Firstly, ADRM addresses overfitting in rehearsal memory by employing FGSM to diversify and increase the complexity of the memory buffer. Secondly, we demonstrate that ADRM mitigates memory overfitting and significantly improves the robustness of CL models, which is crucial for safety-critical applications. Finally, our detailed analysis of features and visualization demonstrates that ADRM mitigates feature drifts in CL memory samples, significantly reducing catastrophic forgetting and resulting in a more resilient CL model. Additionally, our in-depth t-SNE visualizations of feature distribution and the quantification of the feature similarity further enrich our understanding of feature representation in existing CL approaches. Our code is publically available at https://github.com/hikmatkhan/ADRM.

cs.LG↗

arXiv2024

HoneyBee: A Scalable Modular Framework for Creating Multimodal Oncology Datasets with Foundational Embedding Models

HONeYBEE (Harmonized ONcologY Biomedical Embedding Encoder) is an open-source framework that integrates multimodal biomedical data for oncology applications. It processes clinical data (structured and unstructured), whole-slide images, radiology scans, and molecular profiles to generate unified patient-level embeddings using domain-specific foundation models and fusion strategies. These embeddings enable survival prediction, cancer-type classification, patient similarity retrieval, and cohort clustering. Evaluated on 11,400+ patients across 33 cancer types from The Cancer Genome Atlas (TCGA), clinical embeddings showed the strongest single-modality performance with 98.5% classification accuracy and 96.4% precision@10 in patient retrieval. They also achieved the highest survival prediction concordance indices across most cancer types. Multimodal fusion provided complementary benefits for specific cancers, improving overall survival prediction beyond clinical features alone. Comparative evaluation of four large language models revealed that general-purpose models like Qwen3 outperformed specialized medical models for clinical text representation, though task-specific fine-tuning improved performance on heterogeneous data such as pathology reports.

cs.LG↗

arXiv2024

Self-Normalizing Foundation Model for Enhanced Multi-Omics Data Analysis in Oncology

Multi-omics research has enhanced our understanding of cancer heterogeneity and progression. Investigating molecular data through multi-omics approaches is crucial for unraveling the complex biological mechanisms underlying cancer, thereby enabling more effective diagnosis, treatment, and prevention strategies. However, predicting patient outcomes through the integration of all available multi-omics data is still an under-study research direction. Here, we present SeNMo, a foundation model that has been trained on multi-omics data across 33 cancer types. SeNMo is particularly efficient in handling multi-omics data characterized by high-width and low-length attributes. We trained SeNMo for the task of overall survival of patients using pan-cancer multi-omics data involving 33 cancer sites from the GDC. The training multi-omics data includes gene expression, DNA methylation, miRNA expression, DNA mutations, protein expression modalities, and clinical data. SeNMo was validated on two independent cohorts: Moffitt Cancer Center and CPTAC lung squamous cell carcinoma. We evaluated the model's performance in predicting patient's overall survival using the C-Index. SeNMo performed consistently well in the training regime, reflected by the validation C-Index of 0.76 on GDC's public data. In the testing regime, SeNMo performed with a C-Index of 0.758 on a held-out test set. The model showed an average accuracy of 99.8% on the task of classifying the primary cancer type on the pan-cancer test cohort. SeNMo demonstrated robust performance on the classification task of predicting the primary cancer type of patients. SeNMo further demonstrated significant performance in predicting tertiary lymph structures from multi-omics data, showing generalizability across cancer types, molecular data types, and clinical endpoints.

cs.LG↗

arXiv2024

Brain-Inspired Continual Learning-Robust Feature Distillation and Re-Consolidation for Class Incremental Learning

Artificial intelligence (AI) and neuroscience share a rich history, with advancements in neuroscience shaping the development of AI systems capable of human-like knowledge retention. Leveraging insights from neuroscience and existing research in adversarial and continual learning, we introduce a novel framework comprising two core concepts: feature distillation and re-consolidation. Our framework, named Robust Rehearsal, addresses the challenge of catastrophic forgetting inherent in continual learning (CL) systems by distilling and rehearsing robust features. Inspired by the mammalian brain's memory consolidation process, Robust Rehearsal aims to emulate the rehearsal of distilled experiences during learning tasks. Additionally, it mimics memory re-consolidation, where new experiences influence the integration of past experiences to mitigate forgetting. Extensive experiments conducted on CIFAR10, CIFAR100, and real-world helicopter attitude datasets showcase the superior performance of CL models trained with Robust Rehearsal compared to baseline methods. Furthermore, examining different optimization training objectives-joint, continual, and adversarial learning-we highlight the crucial role of feature learning in model performance. This underscores the significance of rehearsing CL-robust samples in mitigating catastrophic forgetting. In conclusion, aligning CL approaches with neuroscience insights offers promising solutions to the challenge of catastrophic forgetting, paving the way for more robust and human-like AI systems.

cs.LG↗

arXiv2024

Vision-Language Models for Medical Report Generation and Visual Question Answering: A Review

Medical vision-language models (VLMs) combine computer vision (CV) and natural language processing (NLP) to analyze visual and textual medical data. Our paper reviews recent advancements in developing VLMs specialized for healthcare, focusing on models designed for medical report generation and visual question answering (VQA). We provide background on NLP and CV, explaining how techniques from both fields are integrated into VLMs to enable learning from multimodal data. Key areas we address include the exploration of medical vision-language datasets, in-depth analyses of architectures and pre-training strategies employed in recent noteworthy medical VLMs, and comprehensive discussion on evaluation metrics for assessing VLMs' performance in medical report generation and VQA. We also highlight current challenges and propose future directions, including enhancing clinical validity and addressing patient privacy concerns. Overall, our review summarizes recent progress in developing VLMs to harness multimodal medical data for improved healthcare applications.

cs.CV↗