arXiv subjects

Tianpeng Deng

Publications and source records attributed to Tianpeng Deng.

3 recordsLinked to original sources

arXiv2026

RapidMitDet: Boosting Computational Efficiency for Mitosis Detection via Magnification Alignment

Automated mitosis detection is a critical research focus, enabling pathologists to rapidly assess mitotic indices for tumor malignancy evaluation. However, most of the existing detection approaches suffer from significant computational inefficiency due to the giga-pixel image resolution of Whole-Slide Images (WSIs), which greatly hinders their clinical applicability. In this study, we propose RapidMitDet, a computational efficient mitosis detection approach. Our method employs a coarse-to-fine framework, first identifying mitotic candidates at lower magnification and then confirming them at higher magnification. In the coarse-detection stage, we introduce magnification-aligned knowledge distillation to reduce the information gap between magnification levels while minimizing the performance degradation in the lower magnification detection model. In the subsequent fine-classification stage, we propose adaptive triplet learning (ATL) to optimize infomative sample selection, thereby enhancing discrimination between mitotic and non-mitotic instances. Experimental results show that RapidMitDet achieves the optimal accuracy-efficiency balance at 20x magnification, improving computational speed by up to 5.62 times over the latest state-of-the-art (SOTA) methods. Due to its lightweight model design, RapidMitDet can also deliver efficient detection at higher magnification (40x) while achieving even higher detection performance. In WSI-level evaluations, our method shows strong agreement with pathologists' diagnoses (ICCs: 0.879 (40x), 0.822 (20x)) while maintaining superior efficiency, highlighting its potential for clinical application. Code is available at https://github.com/logincat/RapidMitDet

eess.IV↗

arXiv2025

Towards Computation- and Communication-efficient Computational Pathology

Despite the impressive performance across a wide range of applications, current computational pathology models face significant diagnostic efficiency challenges due to their reliance on high-magnification whole-slide image analysis. This limitation severely compromises their clinical utility, especially in time-sensitive diagnostic scenarios and situations requiring efficient data transfer. To address these issues, we present a novel computation- and communication-efficient framework called Magnification-Aligned Global-Local Transformer (MAG-GLTrans). Our approach significantly reduces computational time, file transfer requirements, and storage overhead by enabling effective analysis using low-magnification inputs rather than high-magnification ones. The key innovation lies in our proposed magnification alignment (MAG) mechanism, which employs self-supervised learning to bridge the information gap between low and high magnification levels by effectively aligning their feature representations. Through extensive evaluation across various fundamental CPath tasks, MAG-GLTrans demonstrates state-of-the-art classification performance while achieving remarkable efficiency gains: up to 10.7 times reduction in computational time and over 20 times reduction in file transfer and storage requirements. Furthermore, we highlight the versatility of our MAG framework through two significant extensions: (1) its applicability as a feature extractor to enhance the efficiency of any CPath architecture, and (2) its compatibility with existing foundation models and histopathology-specific encoders, enabling them to process low-magnification inputs with minimal information loss. These advancements position MAG-GLTrans as a particularly promising solution for time-sensitive applications, especially in the context of intraoperative frozen section diagnosis where both accuracy and efficiency are paramount.

eess.IV↗

arXiv2023

FedDBL: Communication and Data Efficient Federated Deep-Broad Learning for Histopathological Tissue Classification

Histopathological tissue classification is a fundamental task in computational pathology. Deep learning-based models have achieved superior performance but centralized training with data centralization suffers from the privacy leakage problem. Federated learning (FL) can safeguard privacy by keeping training samples locally, but existing FL-based frameworks require a large number of well-annotated training samples and numerous rounds of communication which hinder their practicability in the real-world clinical scenario. In this paper, we propose a universal and lightweight federated learning framework, named Federated Deep-Broad Learning (FedDBL), to achieve superior classification performance with limited training samples and only one-round communication. By simply associating a pre-trained deep learning feature extractor, a fast and lightweight broad learning inference system and a classical federated aggregation approach, FedDBL can dramatically reduce data dependency and improve communication efficiency. Five-fold cross-validation demonstrates that FedDBL greatly outperforms the competitors with only one-round communication and limited training samples, while it even achieves comparable performance with the ones under multiple-round communications. Furthermore, due to the lightweight design and one-round communication, FedDBL reduces the communication burden from 4.6GB to only 276.5KB per client using the ResNet-50 backbone at 50-round training. Since no data or deep model sharing across different clients, the privacy issue is well-solved and the model security is guaranteed with no model inversion attack risk. Code is available at https://github.com/tianpeng-deng/FedDBL.

eess.IV↗