arXiv subjects

Saadia Binte Alam

Publications and source records attributed to Saadia Binte Alam.

7 recordsLinked to original sources

arXiv2026

PelviNeXt: A Modality-Agnostic Hybrid Network for Pelvic Imaging in Women's Health

Women's health remains substantially under-resourced in medical imaging research, with pelvic pathologies such as polycystic ovary syndrome (PCOS) and pelvic fracture both suffering from a scarcity of public, well-annotated benchmark data despite their clinical importance. We introduce PelviNeXt, a modality-agnostic hybrid architecture combining a dense convolutional feature extractor, hierarchical channel-spatial attention (H-CBAM), a multi-scale fusion module (MSFM), and talking-heads multi-head self-attention (TH-MHSA), applied without modification to both pelvic ultrasound and X-ray inputs. While benchmarking PelviNeXt on PCOSGen, the only gynaecologist-annotated public PCOS ultrasound dataset, we identified extensive exact and near-duplicate contamination within and across the dataset. We audit this contamination via perceptual hashing, publicly release a deduplicated version of the dataset, and establish the first integrity-audited evaluation protocol and baseline for PCOSGen under 5-fold cross-validation. On the only publicly available pelvic fracture X-ray dataset (PXR150), PelviNeXt exceeds previously reported state-of-the-art results across accuracy, recall, specificity, and AUROC. Ablation studies confirm that each architectural component contributes to performance on both tasks. Our results demonstrate that a single architecture, applied without task-specific modification, can serve as a reliable foundation for pelvic imaging across modalities in data-scarce, under-researched areas of women's health.

cs.CV↗

arXiv2026

SecondOpinion: Anatomy-Aware Gated Reasoning for Efficient Medical Image Analysis

Deep learning models for medical image analysis typically apply a fixed amount of computation to every input, regardless of case difficulty. Anatomy-guided dual-stream architectures have been shown to improve diagnostic performance, but they evaluate both streams unconditionally, even on cases a single stream could already resolve confidently. We propose SecondOpinion, a framework in which a fast primary stream processes every case, while a second, anatomy-guided stream is invoked only when GateKeeper, a gating mechanism trained explicitly as a binary correctness classifier, judges that the primary stream's prediction needs additional scrutiny, much as a clinician might seek a second opinion on a difficult case. When activated, the two streams are combined through a lightweight cross-attention fusion module. We evaluate SecondOpinion on a unified five-class chest X-ray dataset and a pelvic fracture dataset, the latter including a held-out, harder subset of fractures that are invisible on X-ray but confirmed via CT. SecondOpinion matches or exceeds prior state-of-the-art performance on both tasks, while activating its anatomy-guided stream on only 9.23% of chest X-ray cases, rising to 24.12% on visible fractures and 45.71% on invisible fractures, an activation rate that tracks task difficulty directly. These results suggest that supervising a gating signal toward correctness, rather than relying on unsupervised confidence, allows a model to allocate anatomical reasoning where it is actually needed.

cs.CV↗

arXiv2026

Invisible Yet Detected: PelFANet with Attention-Guided Anatomical Fusion for Pelvic Fracture Diagnosis

Pelvic fractures pose significant diagnostic challenges, particularly in cases where fracture signs are subtle or invisible on standard radiographs. To address this, we introduce PelFANet, a dual-stream attention network that fuses raw pelvic X-rays with segmented bone images to improve fracture classification. The network employs Fused Attention Blocks (FABlocks) to iteratively exchange and refine features from both inputs, capturing global context and localized anatomical detail. Trained in a two-stage pipeline with a segmentation-guided approach, PelFANet demonstrates superior performance over conventional methods. On the AMERI dataset, it achieves 88.68% accuracy and 0.9334 AUC on visible fractures, while generalizing effectively to invisible fracture cases with 82.29% accuracy and 0.8688 AUC, despite not being trained on them. These results highlight the clinical potential of anatomy-aware dual-input architectures for robust fracture detection, especially in scenarios with subtle radiographic presentations.

cs.CV↗

arXiv2026

Mod-Guide: An LLM-based Content Moderation Feedback System to Address Insensitive Speech toward Indigenous Ethnic and Religious Minority Communities

Language operates as a mechanism of both marginalization and resistance, especially for minority communities navigating insensitive and harmful speech online. As content moderation increasingly depends on large language models (LLMs), concerns arise about whether these systems can recognize culturally insensitive speech-language that disregards or marginalizes the cultural and religious perspectives of historically underrepresented communities, often through implicit erasure, misrepresentation, or normative framing, rather than overt hostility. Focusing on Bangladesh's Hindu and Chakma communities -- the country's largest religious and Indigenous ethnic minorities, respectively -- this paper investigates the epistemic limits of LLM-based moderation systems and explores methods for incorporating minority perspectives. We co-created a culturally grounded corpus of insensitive speech with community members and integrated their narratives into moderation pipelines using retrieval augmented generation (RAG). Our tool, Mod-Guide, improves LLM sensitivity to minority viewpoints by leveraging contextual cues derived from lived experience. Through mixed-method evaluations involving both minority and majority participants, we demonstrate that RAG-enhanced moderation responses are more contextually accurate and perceived differently across ethnic lines. This work advances research in human-computer interaction, AI ethics, and social computing by foregrounding restorative justice and hermeneutical inclusion in the design of content moderation systems.

cs.HC↗

arXiv2026

Route, Retrieve, Reflect, Repair: Self-Improving Agentic Framework for Visual Detection and Linguistic Reasoning in Medical Imaging

Medical image analysis increasingly relies on large vision-language models (VLMs), yet most systems remain single-pass black boxes that offer limited control over reasoning, safety, and spatial grounding. We propose R^4, an agentic framework that decomposes medical imaging workflows into four coordinated agents: a Router that configures task- and specialization-aware prompts from the image, patient history, and metadata; a Retriever that uses exemplar memory and pass@k sampling to jointly generate free-text reports and bounding boxes; a Reflector that critiques each draft-box pair for key clinical error modes (negation, laterality, unsupported claims, contradictions, missing findings, and localization errors); and a Repairer that iteratively revises both narrative and spatial outputs under targeted constraints while curating high-quality exemplars for future cases. Instantiated on chest X-ray analysis with multiple modern VLM backbones and evaluated on report generation and weakly supervised detection, R^4 consistently boosts LLM-as-a-Judge scores by roughly +1.7-+2.5 points and mAP50 by +2.5-+3.5 absolute points over strong single-VLM baselines, without any gradient-based fine-tuning. These results show that agentic routing, reflection, and repair can turn strong but brittle VLMs into more reliable and better grounded tools for clinical image interpretation. Our code can be found at: https://github.com/faiyazabdullah/MultimodalMedAgent

cs.CV↗

arXiv2024

A Civics-oriented Approach to Understanding Intersectionally Marginalized Users' Experience with Hate Speech Online

While content moderation in online platforms marginalizes users in the Global South at large, users of certain identities are further marginalized. Such users often come from Indigenous ethnic minority groups or identify as women. Through a qualitative study based on 18 semi-structured interviews, this paper explores how such users' experiences with hate speech online in Bangladesh are shaped by their intersectional identities. Through a civics-oriented approach, we examined the spectrum of their legal status, membership, rights, and participation as users of online platforms. Drawing analogies with the concept of citizenship, we develop the concept of usership that offers a user-centered metaphor in studying moderation and platform governance.

cs.HC↗

arXiv2023

A Novel 1D Generative Adversarial Network-based Framework for Atrial Fibrillation Detection using Restored Wrist Photoplethysmography Signals

Atrial fibrillation (AF) increases the risk of stroke. Electrocardiogram (ECG) is used for AF detection, while photoplethysmography (PPG) is simple to use and appropriate for long-term monitoring. We have developed a novel approach to detect AF from smartwatch-based wrist PPG signals. To the best of our knowledge, this is the first study to employ 1D CycleGAN for the reconstruction of 1D wrist PPG signals, since the quality of wrist PPG signals is very poor due to motion artifacts and acquisition site limitations. Our proposed approach is validated on a dataset of 21,278 10s long wrist PPG segments. The dataset was divided into two halves and two experiments were conducted. One half was used for training and the other half for testing and vice versa. Our classification model (Self-AFNet) with 1D-CycleGAN for restoration achieves an accuracy of 96.41% and 97.09% for both splits, respectively. There is a noteworthy improvement in accuracy (2.94% and 5.08% for test splits, respectively) for restored signals as compared to unrestored PPG. AF detection task was also performed using ECG signals with the matched PPG signals to assess the validity of employing reconstructed PPG-based AF classification. Self-AFNet managed to achieve an accuracy of 98.07% and 98.97%, respectively using two ECG splits which is comparable to the performance of AF detection utilizing reconstructed PPG segments. This study reflects that reconstructed wrist PPG signals acquired from wearable devices can be used for reliable detection of atrial fibrillation, which can significantly help in the reduction of the risk of stroke.

eess.SP↗