Author name cluster

Longfei Han

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

1 author row

JBHI Journal 2025 Journal Article

MHKD: Multi-Step Hybrid Knowledge Distillation for Low-Resolution Whole Slide Images Glomerulus Detection

Xiangsen Zhang
Longfei Han
Chenchu Xu
Zhaohui Zheng
Jin Ding
Xianghui Fu
Dingwen Zhang
Junwei Han

Glomerulus detection is a critical component of renal histopathology assessment, essential for diagnosing glomerulonephritis. To mitigate the increasing workload on pathologists, AI-assisted diagnostic methods based on high-resolution digital pathology whole slide images have been developed. However, these current AI-assisted approaches are limited to high-resolution whole slide images, necessitating expensive digital scanner equipment, high image storage costs, and significant computational complexity. To address this limitation, this paper pioneers a method for facilitating glomerulus detection in low-resolution human kidney pathology images. Specifically, we propose a novel multi-step hybrid knowledge distillation method. Our method distills both the global features and the semantic information through a hybrid knowledge distillation strategy that integrates offline and online knowledge distillation, where the information from high-resolution pathological images is successively transferred to student model from the global features in the shallow network layers to the semantic information of the back-end through a multi-step training strategy. Experimental results on two datasets show that the proposed method achieves effective detection outcomes for low-resolution kidney pathology images. Compared to other state-of-the-art detection techniques, our method achieves an ${AP}_{0. 5: 0. 95}$ improvement of 23. 1% on the private LN dataset and 15. 9% on the public HUBMAP dataset.

Details DOI

AAAI Conference 2024 Conference Paper

RL-SeqISP: Reinforcement Learning-Based Sequential Optimization for Image Signal Processing

Xinyu Sun
Zhikun Zhao
Lili Wei
Congyan Lang
Mingxuan Cai
Longfei Han
Juan Wang
Bing Li

Hardware image signal processing (ISP), aiming at converting RAW inputs to RGB images, consists of a series of processing blocks, each with multiple parameters. Traditionally, ISP parameters are manually tuned in isolation by imaging experts according to application-specific quality and performance metrics, which is time-consuming and biased towards human perception due to complex interaction with the output image. Since the relationship between any single parameter’s variation and the output performance metric is a complex, non-linear function, optimizing such a large number of ISP parameters is challenging. To address this challenge, we propose a novel Sequential ISP parameter optimization model, called the RL-SeqISP model, which utilizes deep reinforcement learning to jointly optimize all ISP parameters for a variety of imaging applications. Concretely, inspired by the sequential tuning process of human experts, the proposed model can progressively enhance image quality by seamlessly integrating information from both the image feature space and the parameter space. Furthermore, a dynamic parameter optimization module is introduced to avoid ISP parameters getting stuck into local optima, which is able to more effectively guarantee the optimal parameters resulting from the sequential learning strategy. These merits of the RL-SeqISP model as well as its high efficiency are substantiated by comprehensive experiments on a wide range of downstream tasks, including two visual analysis tasks (instance segmentation and object detection), and image quality assessment (IQA), as compared with representative methods both quantitatively and qualitatively. In particular, even using only 10% of the training data, our model outperforms other SOTA methods by an average of 7% mAP on two visual analysis tasks.

PDF Details DOI

JBHI Journal 2023 Journal Article

BMAnet: Boundary Mining With Adversarial Learning for Semi-Supervised 2D Myocardial Infarction Segmentation

Chenchu Xu
Yifei Wang
Dong Zhang
Longfei Han
Yanping Zhang
Jie Chen
Shuo Li

Automatic segmentation of myocardial infarction (MI) regions in late gadolinium-enhanced cardiac magnetic resonance images is an essential step in the computed diagnosis of myocardial infarction. Most of the current myocardial infarction region segmentation methods are based on fully supervised deep learning. However, cardiologists' annotation of myocardial infarction regions in cardiac magnetic resonance images during the diagnosis process is time-consuming and expensive. This paper proposes a semi-supervised myocardial infarction segmentation. It consists of two models: 1) a boundary mining model and 2) an adversarial learning model. The boundary mining model can solve the boundary ambiguity problem by enlarging the gap between the foreground and background features, thus segmenting the myocardial infarction region accurately. The adversarial learning model can make the boundary mining model learn from additional unlabeled data by evaluating the segmentation performance and providing pseudo supervision, which significantly increases the robustness of the boundary mining model. We conduct extensive experiments on an in-house myocardial magnetic resonance dataset. The experimental results on six evaluation metrics demonstrate that our method achieves excellent results in myocardial infarction segmentation and outperforms the state-of-the-art semi-supervised methods.

Details DOI

AIIM Journal 2020 Journal Article

Deep supervised learning with mixture of neural networks

Yaxian Hu
Senlin Luo
Longfei Han
Limin Pan
Tiemei Zhang

Deep Neural Network (DNN), as a deep architectures, has shown excellent performance in classification tasks. However, when the data has different distributions or contains some latent non-observed factors, it is difficult for DNN to train a single model to perform well on the classification tasks. In this paper, we propose mixture model based on DNNs (MoNNs), a supervised approach to perform classification tasks with a gating network and multiple local expert models. We use a neural network as a gating function and use DNNs as local expert models. The gating network split the heterogeneous data into several homogeneous components. DNNs are combined to perform classification tasks in each component. Moreover, we use EM (Expectation Maximization) as an optimization algorithm. Experiments proved that our MoNNs outperformed the other compared methods on determination of diabetes, determination of benign or malignant breast cancer, and handwriting recognition. Therefore, the MoNNs can solve the problem of data heterogeneity and have a good effect on classification tasks.

Details DOI

JBHI Journal 2017 Journal Article

An Intelligible Risk Stratification Model Based on Pairwise and Size Constrained Kmeans

Longfei Han
Senlin Luo
Huaiqing Wang
Limin Pan
Xincheng Ma
Tiemei Zhang

Having a system to stratify individuals according to risk is key to clinical disease prevention. This allows individuals identified at different risk tiers to benefit from further investigation and intervention. But the same risk score estimated for two different persons does not mean they need the same further investigation or represent the similarity health condition between two persons. Meanwhile, users still do not know a prior what most of the risk tiers are, and how many tiers should be found in risk stratification. In this paper, the proposed pairwise and size constrained Kmeans (PSCKmeans) method simultaneously integrates the limited supervised information and the size constraints to screen the high-risk population based on similarity measurement, and gets a feasible and balanced stratification solution to avoid cluster with few points. Results on China Health and Nutrition Survey public dataset and follow-up dataset show that the proposed PSCKmeans method can naturally grade the risk of diabetes into four tiers, and achieve 73. 8%, 85. 1%, and 0. 95% sensitivity, specificity, and ratio of minimum to expected on testing data. The proposed method compares favorably with eight previous semisupervised clustering methods; it demonstrates that semisupervised clustering by unifying multiple forms of constraints can guide a good partition that is more relevant for the domain and find new categories through prior knowledge. Finally, this risk stratification model can provide a tool for risk stratification of clinical disease and be used for further intervention for people with similar health condition.

Details DOI

IJCAI Conference 2017 Conference Paper

Self-paced Mixture of Regressions

Longfei Han
Dingwen Zhang
Dong Huang
Xiaojun Chang
Jun Ren
Senlin Luo
Junwei Han

Mixture of regressions (MoR) is the well-established and effective approach to model discontinuous and heterogeneous data in regression problems. Existing MoR approaches assume smooth joint distribution for its good anlaytic properties. However, such assumption makes existing MoR very sensitive to intra-component outliers (the noisy training data residing in certain components) and the inter-component imbalance (the different amounts of training data in different components). In this paper, we make the earliest effort on Self-paced Learning (SPL) in MoR, i. e. , Self-paced mixture of regressions (SPMoR) model. We propose a novel self-paced regularizer based on the Exclusive LASSO, which improves inter-component balance of training data. As a robust learning regime, SPL pursues confidence sample reasoning. To demonstrate the effectiveness of SPMoR, we conducted experiments on both the sythetic examples and real-world applications to age estimation and glucose estimation. The results show that SPMoR outperforms the state-of-the-arts methods.

PDF Details

JBHI Journal 2015 Journal Article

Rule Extraction From Support Vector Machines Using Ensemble Learning Approach: An Application for Diagnosis of Diabetes

Longfei Han
Senlin Luo
Jianmin Yu
Limin Pan
Songjing Chen

Diabetes mellitus is a chronic disease and a worldwide public health challenge. It has been shown that 50–80% proportion of T2DM is undiagnosed. In this paper, support vector machines are utilized to screen diabetes, and an ensemble learning module is added, which turns the “black box” of SVM decisions into comprehensible and transparent rules, and it is also useful for solving imbalance problem. Results on China Health and Nutrition Survey data show that the proposed ensemble learning method generates rule sets with weighted average precision 94. 2% and weighted average recall 93. 9% for all classes. Furthermore, the hybrid system can provide a tool for diagnosis of diabetes, and it supports a second opinion for lay users.

Details DOI