arXiv subjects

Mingzhe Hu

Publications and source records attributed to Mingzhe Hu.

34 records · Page 2Linked to original sources

arXiv2025

Unifying Biomedical Vision-Language Expertise: Towards a Generalist Foundation Model via Multi-CLIP Knowledge Distillation

CLIP models pretrained on natural images with billion-scale image-text pairs have demonstrated impressive capabilities in zero-shot classification, cross-modal retrieval, and open-ended visual answering. However, transferring this success to biomedicine is hindered by the scarcity of large-scale biomedical image-text corpora, the heterogeneity of image modalities, and fragmented data standards across institutions. These limitations hinder the development of a unified and generalizable biomedical foundation model trained from scratch. To overcome this, we introduce MMKD-CLIP, a generalist biomedical foundation model developed via Multiple Medical CLIP Knowledge Distillation. Rather than relying on billion-scale raw data, MMKD-CLIP distills knowledge from nine state-of-the-art domain-specific or generalist biomedical CLIP models, each pretrained on millions of biomedical image-text pairs. Our two-stage training pipeline first performs CLIP-style pretraining on over 2.9 million biomedical image-text pairs from 26 image modalities, followed by feature-level distillation using over 19.2 million feature pairs extracted from teacher models. We evaluate MMKD-CLIP on 58 diverse biomedical datasets, encompassing over 10.8 million biomedical images across nine image modalities. The evaluation spans six core task types: zero-shot classification, linear probing, cross-modal retrieval, visual question answering, survival prediction, and cancer diagnosis. MMKD-CLIP consistently outperforms all teacher models while demonstrating remarkable robustness and generalization across image domains and task settings. These results underscore that multi-teacher knowledge distillation is a scalable and effective paradigm for building high-performing biomedical foundation models under the practical constraints of real-world data availability.

cs.CV↗

arXiv2025

Limited-Angle CBCT Reconstruction via Geometry-Integrated Cycle-domain Denoising Diffusion Probabilistic Models

Cone-beam CT (CBCT) is widely used in clinical radiotherapy for image-guided treatment, improving setup accuracy, adaptive planning, and motion management. However, slow gantry rotation limits performance by introducing motion artifacts, blurring, and increased dose. This work aims to develop a clinically feasible method for reconstructing high-quality CBCT volumes from consecutive limited-angle acquisitions, addressing imaging challenges in time- or dose-constrained settings. We propose a limited-angle (LA) geometry-integrated cycle-domain (LA-GICD) framework for CBCT reconstruction, comprising two denoising diffusion probabilistic models (DDPMs) connected via analytic cone-beam forward and back projectors. A Projection-DDPM completes missing projections, followed by back-projection, and an Image-DDPM refines the volume. This dual-domain design leverages complementary priors from projection and image spaces to achieve high-quality reconstructions from limited-angle (<= 90 degrees) scans. Performance was evaluated against full-angle reconstruction. Four board-certified medical physicists conducted assessments. A total of 78 planning CTs in common CBCT geometries were used for training and evaluation. The method achieved a mean absolute error of 35.5 HU, SSIM of 0.84, and PSNR of 29.8 dB, with visibly reduced artifacts and improved soft-tissue clarity. LA-GICD's geometry-aware dual-domain learning, embedded in analytic forward/backward operators, enabled artifact-free, high-contrast reconstructions from a single 90-degree scan, reducing acquisition time and dose four-fold. LA-GICD improves limited-angle CBCT reconstruction with strong data fidelity and anatomical realism. It offers a practical solution for short-arc acquisitions, enhancing CBCT use in radiotherapy by providing clinically applicable images with reduced scan time and dose for more accurate, personalized treatments.

cs.CV↗

arXiv2025

A Large Convolutional Neural Network for Clinical Target and Multi-organ Segmentation in Gynecologic Brachytherapy with Multi-stage Learning

Purpose: Accurate segmentation of clinical target volumes (CTV) and organs-at-risk is crucial for optimizing gynecologic brachytherapy (GYN-BT) treatment planning. However, anatomical variability, low soft-tissue contrast in CT imaging, and limited annotated datasets pose significant challenges. This study presents GynBTNet, a novel multi-stage learning framework designed to enhance segmentation performance through self-supervised pretraining and hierarchical fine-tuning strategies. Methods: GynBTNet employs a three-stage training strategy: (1) self-supervised pretraining on large-scale CT datasets using sparse submanifold convolution to capture robust anatomical representations, (2) supervised fine-tuning on a comprehensive multi-organ segmentation dataset to refine feature extraction, and (3) task-specific fine-tuning on a dedicated GYN-BT dataset to optimize segmentation performance for clinical applications. The model was evaluated against state-of-the-art methods using the Dice Similarity Coefficient (DSC), 95th percentile Hausdorff Distance (HD95), and Average Surface Distance (ASD). Results: Our GynBTNet achieved superior segmentation performance, significantly outperforming nnU-Net and Swin-UNETR. Notably, it yielded a DSC of 0.837 +/- 0.068 for CTV, 0.940 +/- 0.052 for the bladder, 0.842 +/- 0.070 for the rectum, and 0.871 +/- 0.047 for the uterus, with reduced HD95 and ASD compared to baseline models. Self-supervised pretraining led to consistent performance improvements, particularly for structures with complex boundaries. However, segmentation of the sigmoid colon remained challenging, likely due to anatomical ambiguities and inter-patient variability. Statistical significance analysis confirmed that GynBTNet's improvements were significant compared to baseline models.

cs.CV↗

arXiv2025

RoMedFormer: A Rotary-Embedding Transformer Foundation Model for 3D Genito-Pelvic Structure Segmentation in MRI and CT

Deep learning-based segmentation of genito-pelvic structures in MRI and CT is crucial for applications such as radiation therapy, surgical planning, and disease diagnosis. However, existing segmentation models often struggle with generalizability across imaging modalities, and anatomical variations. In this work, we propose RoMedFormer, a rotary-embedding transformer-based foundation model designed for 3D female genito-pelvic structure segmentation in both MRI and CT. RoMedFormer leverages self-supervised learning and rotary positional embeddings to enhance spatial feature representation and capture long-range dependencies in 3D medical data. We pre-train our model using a diverse dataset of 3D MRI and CT scans and fine-tune it for downstream segmentation tasks. Experimental results demonstrate that RoMedFormer achieves superior performance segmenting genito-pelvic organs. Our findings highlight the potential of transformer-based architectures in medical image segmentation and pave the way for more transferable segmentation frameworks.

eess.IV↗

arXiv2024

Current Progress of Digital Twin Construction Using Medical Imaging

Medical imaging has played a pivotal role in advancing and refining digital twin technology, allowing for the development of highly personalized virtual models that represent human anatomy and physiological functions. A key component in constructing these digital twins is the integration of high-resolution imaging data, such as MRI, CT, PET, and ultrasound, with sophisticated computational models. Advances in medical imaging significantly enhance real-time simulation, predictive modeling, and early disease diagnosis, individualized treatment planning, ultimately boosting precision and personalized care. Although challenges persist, such as the complexity of anatomical modeling, integrating various imaging modalities, and high computational demands, recent progress in imaging and machine learning has greatly improved the precision and clinical applicability of digital twins. This review investigates the role of medical imaging in developing digital twins across organ systems. Key findings demonstrate that improvements in medical imaging have enhanced the diagnostic and therapeutic potential of digital twins beyond traditional methods, particularly in imaging accuracy, treatment effectiveness, and patient outcomes. The review also examines the technical barriers that currently limit further development of digital twin technology, despite advances in medical imaging, and outlines future research avenues aimed at overcoming these challenges to unlock the full potential of this technology in precision medicine.

physics.med-ph↗

arXiv2024

Discovery of a metallic room-temperature d-wave altermagnet KV2Se2O

Beyond conventional ferromagnetism and antiferromagnetism, altermagnetism is a recently discovered unconventional magnetic phase characterized by time-reversal symmetry breaking and spin-split band structures in materials with zero net magnetization. This distinct magnetic phase not only enriches the understanding of fundamental physical concepts but also has profound impacts on condense-matter physics research and practical device applications. Spin-polarized band structures have been recently observed in semiconductors MnTe and MnTe2 with vanishing net magnetization, confirming the existence of this unconventional magnetic order. Metallic altermagnets have unique advantages for exploring novel physical phenomena related to low-energy quasiparticle excitations and for applications in spintronics as electrical conductivity in metals allows the direct manipulation of spin current through electric field. Here, through comprehensive characterization and analysis of the magnetic and electronic structures of KV2Se2O, we have unambiguously demonstrated a metallic room-temperature altermaget with d-wave spin-momentum locking. The highly anisotropic spin-polarized Fermi surfaces and the spin-density-wave order emerging in the altermagnetic phase make it an extraordinary platform for designing high-performance spintronic devices and studying many-body effects coupled with the unconventional magnetism.

cond-mat.mtrl-sci↗

arXiv2024

Nonvolatile optical control of interlayer stacking order in 1T-TaS2

Nonvolatile optical manipulation of material properties on demand is a highly sought-after feature in the advancement of future optoelectronic applications. While the discovery of such metastable transition in various materials holds good promise for achieving this goal, their practical implementation is still in the nascent stage. Here, we unravel the nature of the ultrafast laser-induced hidden state in 1T-TaS2 by systematically characterizing the electronic structure evolution throughout the reversible transition cycle. We identify it as a mixed-stacking state involving two similarly low-energy interlayer orders, which is manifested as the charge density wave phase disruption. Furthermore, our comparative experiments utilizing the single-pulse writing, pulse-train erasing and pulse-pair control explicitly reveal the distinct mechanism of the bidirectional transformations -- the ultrafast formation of the hidden state is initiated by a coherent phonon which triggers a competition of interlayer stacking orders, while its recovery to the initial state is governed by the progressive domain coarsening. Our work highlights the deterministic role of the competing interlayer orders in the nonvolatile phase transition in the layered material 1T-TaS2, and promises the coherent control of the phase transition and switching speed. More importantly, these results establish all-optical engineering of stacking orders in low-dimensional materials as a viable strategy for achieving desirable nonvolatile electronic devices.

cond-mat.mtrl-sci↗

arXiv2024

Mammo-CLIP: Leveraging Contrastive Language-Image Pre-training (CLIP) for Enhanced Breast Cancer Diagnosis with Multi-view Mammography

Although fusion of information from multiple views of mammograms plays an important role to increase accuracy of breast cancer detection, developing multi-view mammograms-based computer-aided diagnosis (CAD) schemes still faces challenges and no such CAD schemes have been used in clinical practice. To overcome the challenges, we investigate a new approach based on Contrastive Language-Image Pre-training (CLIP), which has sparked interest across various medical imaging tasks. By solving the challenges in (1) effectively adapting the single-view CLIP for multi-view feature fusion and (2) efficiently fine-tuning this parameter-dense model with limited samples and computational resources, we introduce Mammo-CLIP, the first multi-modal framework to process multi-view mammograms and corresponding simple texts. Mammo-CLIP uses an early feature fusion strategy to learn multi-view relationships in four mammograms acquired from the CC and MLO views of the left and right breasts. To enhance learning efficiency, plug-and-play adapters are added into CLIP image and text encoders for fine-tuning parameters and limiting updates to about 1% of the parameters. For framework evaluation, we assembled two datasets retrospectively. The first dataset, comprising 470 malignant and 479 benign cases, was used for few-shot fine-tuning and internal evaluation of the proposed Mammo-CLIP via 5-fold cross-validation. The second dataset, including 60 malignant and 294 benign cases, was used to test generalizability of Mammo-CLIP. Study results show that Mammo-CLIP outperforms the state-of-art cross-view transformer in AUC (0.841 vs. 0.817, 0.837 vs. 0.807) on both datasets. It also surpasses previous two CLIP-based methods by 20.3% and 14.3%. This study highlights the potential of applying the finetuned vision-language models for developing next-generation, image-text-based CAD schemes of breast cancer.

cs.CV↗

arXiv2024

Anisotropic magnetism and band evolution induced by ferromagnetic phase transition in titanium-based kagome ferromagnet SmTi3Bi4

Kagome magnets with diverse topological quantum responses are crucial for next-generation topological engineering. The anisotropic magnetism and band evolution induced by ferromagnetic phase transition (FMPT) is reported in a newly discovered titanium-based kagome ferromagnet S mTi3 Bi4, which features a distorted Ti kagome lattice and S m atomic zig-zag chains. Temperature-dependent resistivity, heat capacity, and magnetic susceptibility reveal a ferromagnetic ordering temperature Tc of 23.2 K. A large magnetic anisotropy, observed by applying the magnetic field along three crystallographic axes, identifies the b axis as the easy axis. Angle-resolved photoemission spectroscopy with first-principles calculations unveils the characteristic kagome motif, including the Dirac point at the Fermi level and multiple van Hove singularities. Notably, a band splitting and gap closing attributed to FMPT is observed, originating from the exchange coupling between S m 4 f local moments and itinerant electrons of the kagome Ti atoms, as well as the time-reversal symmetry breaking induced by the long-range ferromagnetic order. Considering the large in-plane magnetization and the evolution of electronic structure under the influence of ferromagnetic ordering, such materials promise to be a new platform for exploring the intricate electronic properties and magnetic phases based on the kagome lattice.

cond-mat.mtrl-sci↗

arXiv2023

Attention-Driven Lightweight Model for Pigmented Skin Lesion Detection

This study presents a lightweight pipeline for skin lesion detection, addressing the challenges posed by imbalanced class distribution and subtle or atypical appearances of some lesions. The pipeline is built around a lightweight model that leverages ghosted features and the DFC attention mechanism to reduce computational complexity while maintaining high performance. The model was trained on the HAM10000 dataset, which includes various types of skin lesions. To address the class imbalance in the dataset, the synthetic minority over-sampling technique and various image augmentation techniques were used. The model also incorporates a knowledge-based loss weighting technique, which assigns different weights to the loss function at the class level and the instance level, helping the model focus on minority classes and challenging samples. This technique involves assigning different weights to the loss function on two levels - the class level and the instance level. By applying appropriate loss weights, the model pays more attention to the minority classes and challenging samples, thus improving its ability to correctly detect and classify different skin lesions. The model achieved an accuracy of 92.4%, a precision of 84.2%, a recall of 86.9%, a f1-score of 85.4% with particularly strong performance in identifying Benign Keratosis-like lesions (BKL) and Nevus (NV). Despite its superior performance, the model's computational cost is considerably lower than some models with less accuracy, making it an optimal solution for real-world applications where both accuracy and efficiency are essential.

cs.CV↗

arXiv2023

BreastSAM: A Study of Segment Anything Model for Breast Tumor Detection in Ultrasound Images

Breast cancer is one of the most common cancers among women worldwide, with early detection significantly increasing survival rates. Ultrasound imaging is a critical diagnostic tool that aids in early detection by providing real-time imaging of the breast tissue. We conducted a thorough investigation of the Segment Anything Model (SAM) for the task of interactive segmentation of breast tumors in ultrasound images. We explored three pre-trained model variants: ViT_h, ViT_l, and ViT_b, among which ViT_l demonstrated superior performance in terms of mean pixel accuracy, Dice score, and IoU score. The significance of prompt interaction in improving the model's segmentation performance was also highlighted, with substantial improvements in performance metrics when prompts were incorporated. The study further evaluated the model's differential performance in segmenting malignant and benign breast tumors, with the model showing exceptional proficiency in both categories, albeit with slightly better performance for benign tumors. Furthermore, we analyzed the impacts of various breast tumor characteristics - size, contrast, aspect ratio, and complexity - on segmentation performance. Our findings reveal that tumor contrast and size positively impact the segmentation result, while complex boundaries pose challenges. The study provides valuable insights for using SAM as a robust and effective algorithm for breast tumor segmentation in ultrasound images.

eess.IV↗

arXiv2023

Polyp-SAM: Transfer SAM for Polyp Segmentation

Colon polyps are considered important precursors for colorectal cancer. Automatic segmentation of colon polyps can significantly reduce the misdiagnosis of colon cancer and improve physician annotation efficiency. While many methods have been proposed for polyp segmentation, training large-scale segmentation networks with limited colonoscopy data remains a challenge. Recently, the Segment Anything Model (SAM) has recently gained much attention in both natural and medical image segmentation. SAM demonstrates superior performance in several image benchmarks and therefore shows great potential for medical image segmentation. In this study, we propose Poly-SAM, a finetuned SAM model for polyp segmentation, and compare its performance to several state-of-the-art polyp segmentation models. We also compare two transfer learning strategies of SAM with and without finetuning its encoders. Evaluated on five public datasets, our Polyp-SAM achieves state-of-the-art performance on two datasets and impressive performance on three datasets, with dice scores all above 88%. This study demonstrates the great potential of adapting SAM to medical image segmentation tasks. We plan to release the code and model weights for this paper at: https://github.com/ricklisz/Polyp-SAM.

eess.IV↗

arXiv2023

SkinSAM: Empowering Skin Cancer Segmentation with Segment Anything Model

Skin cancer is a prevalent and potentially fatal disease that requires accurate and efficient diagnosis and treatment. Although manual tracing is the current standard in clinics, automated tools are desired to reduce human labor and improve accuracy. However, developing such tools is challenging due to the highly variable appearance of skin cancers and complex objects in the background. In this paper, we present SkinSAM, a fine-tuned model based on the Segment Anything Model that showed outstanding segmentation performance. The models are validated on HAM10000 dataset which includes 10015 dermatoscopic images. While larger models (ViT_L, ViT_H) performed better than the smaller one (ViT_b), the finetuned model (ViT_b_finetuned) exhibited the greatest improvement, with a Mean pixel accuracy of 0.945, Mean dice score of 0.8879, and Mean IoU score of 0.7843. Among the lesion types, vascular lesions showed the best segmentation results. Our research demonstrates the great potential of adapting SAM to medical image segmentation tasks.

cs.CV↗

arXiv2023

Advancing Medical Imaging with Language Models: A Journey from N-grams to ChatGPT

In this paper, we aimed to provide a review and tutorial for researchers in the field of medical imaging using language models to improve their tasks at hand. We began by providing an overview of the history and concepts of language models, with a special focus on large language models. We then reviewed the current literature on how language models are being used to improve medical imaging, emphasizing different applications such as image captioning, report generation, report classification, finding extraction, visual question answering, interpretable diagnosis, and more for various modalities and organs. The ChatGPT was specially highlighted for researchers to explore more potential applications. We covered the potential benefits of accurate and efficient language models for medical imaging analysis, including improving clinical workflow efficiency, reducing diagnostic errors, and assisting healthcare professionals in providing timely and accurate diagnoses. Overall, our goal was to bridge the gap between language models and medical imaging and inspire new ideas and innovations in this exciting area of research. We hope that this review paper will serve as a useful resource for researchers in this field and encourage further exploration of the possibilities of language models in medical imaging.

cs.CV↗

arXiv2022

Reinforcement Learning in Medical Image Analysis: Concepts, Applications, Challenges, and Future Directions

Motivation: Medical image analysis involves tasks to assist physicians in qualitative and quantitative analysis of lesions or anatomical structures, significantly improving the accuracy and reliability of diagnosis and prognosis. Traditionally, these tasks are finished by physicians or medical physicists and lead to two major problems: (i) low efficiency; (ii) biased by personal experience. In the past decade, many machine learning methods have been applied to accelerate and automate the image analysis process. Compared to the enormous deployments of supervised and unsupervised learning models, attempts to use reinforcement learning in medical image analysis are scarce. This review article could serve as the stepping-stone for related research. Significance: From our observation, though reinforcement learning has gradually gained momentum in recent years, many researchers in the medical analysis field find it hard to understand and deploy in clinics. One cause is lacking well-organized review articles targeting readers lacking professional computer science backgrounds. Rather than providing a comprehensive list of all reinforcement learning models in medical image analysis, this paper may help the readers to learn how to formulate and solve their medical image analysis research as reinforcement learning problems. Approach & Results: We selected published articles from Google Scholar and PubMed. Considering the scarcity of related articles, we also included some outstanding newest preprints. The papers are carefully reviewed and categorized according to the type of image analysis task. We first review the basic concepts and popular models of reinforcement learning. Then we explore the applications of reinforcement learning models in landmark detection. Finally, we conclude the article by discussing the reviewed reinforcement learning approaches' limitations and possible improvements.

cs.CV↗

arXiv2019

Drone-based all-weather entanglement distribution

The quantum satellite is a cornerstone towards practical free-space quantum network and overcomes the photon loss over large distance. However, challenges still exist including real-time all-location coverage and multi-node construction, which may be complemented by the diversity of modern drones. Here we demonstrate the first drone-based entanglement distribution at all-weather conditions over 200 meters (test field limited), and the Clauser-Horne-Shimony-Holt S-parameter exceeds 2.49, within 35 kg take-off weight. With symmetric transmitter and receiver beam apertures and single-mode-fiber-coupling technology, such progress is ready for future quantum network with multi-node expansion. This network can be further integrated in picture-drone sizes for plug-and-play local-area coverage, or loaded onto high-altitude drones for wide-area coverage, which adds flexibility while connecting to the existing satellites and ground fiber-based quantum network.

quant-ph↗