Zhang Li

Yiping Jiao, Jeroen van der Laak, Shadi Albarqouni et al. · eth-zurich

We introduce LYSTO, the Lymphocyte Assessment Hackathon, which was held in conjunction with the MICCAI 2019 Conference in Shenzen (China). The competition required participants to automatically assess the number of lymphocytes, in particular T-cells, in histopathological images of colon, breast, and prostate cancer stained with CD3 and CD8 immunohistochemistry. Differently from other challenges setup in medical image analysis, LYSTO participants were solely given a few hours to address this problem. In this paper, we describe the goal and the multi-phase organization of the hackathon; we describe the proposed methods and the on-site results. Additionally, we present post-competition results where we show how the presented methods perform on an independent set of lung cancer slides, which was not part of the initial competition, as well as a comparison on lymphocyte assessment between presented methods and a panel of pathologists. We show that some of the participants were capable to achieve pathologist-level performance at lymphocyte assessment. After the hackathon, LYSTO was left as a lightweight plug-and-play benchmark dataset on grand-challenge website, together with an automatic evaluation platform. LYSTO has supported a number of research in lymphocyte assessment in oncology. LYSTO will be a long-lasting educational challenge for deep learning and digital pathology, it is available at https://lysto.grand-challenge.org/.

Kun Wang, Zi Wang, Zhang Li et al.

Oriented object detection is a fundamental yet challenging task in remote sensing (RS), aiming to locate and classify objects with arbitrary orientations. Recent advancements in deep learning have significantly enhanced the capabilities of oriented object detection methods. Given the rapid development of this field, a comprehensive survey of the recent advances in oriented object detection is presented in this paper. Specifically, we begin by tracing the technical evolution from horizontal object detection to oriented object detection and highlighting the specific related challenges, including feature misalignment, spatial misalignment, oriented bounding box (OBB) regression problems, and common issues encountered in RS. Subsequently, we further categorize the existing methods into detection frameworks, OBB regression techniques, feature representation approaches, and solutions to common issues and provide an in-depth discussion of how these methods address the above challenges. In addition, we cover several publicly available datasets and evaluation protocols. Furthermore, we provide a comprehensive comparison and analysis involving the state-of-the-art methods. Toward the end of this paper, we identify several future directions for oriented object detection research.

Yuliang Liu, Biao Yang, Qiang Liu et al.

We present TextMonkey, a large multimodal model (LMM) tailored for text-centric tasks. Our approach introduces enhancement across several dimensions: By adopting Shifted Window Attention with zero-initialization, we achieve cross-window connectivity at higher input resolutions and stabilize early training; We hypothesize that images may contain redundant tokens, and by using similarity to filter out significant tokens, we can not only streamline the token length but also enhance the model's performance. Moreover, by expanding our model's capabilities to encompass text spotting and grounding, and incorporating positional information into responses, we enhance interpretability. It also learns to perform screenshot tasks through finetuning. Evaluation on 12 benchmarks shows notable improvements: 5.2% in Scene Text-Centric tasks (including STVQA, TextVQA, and OCRVQA), 6.9% in Document-Oriented tasks (such as DocVQA, InfoVQA, ChartVQA, DeepForm, Kleister Charity, and WikiTableQuestions), and 2.8% in Key Information Extraction tasks (comprising FUNSD, SROIE, and POIE). It outperforms in scene text spotting with a 10.9\% increase and sets a new standard on OCRBench, a comprehensive benchmark consisting of 29 OCR-related assessments, with a score of 561, surpassing previous open-sourced large multimodal models for document understanding. Code will be released at https://github.com/Yuliang-Liu/Monkey.

Sirui Hong, Yizhang Lin, Bang Liu et al. · tencent-ai, tsinghua

Large Language Model (LLM)-based agents have shown effectiveness across many applications. However, their use in data science scenarios requiring solving long-term interconnected tasks, dynamic data adjustments and domain expertise remains challenging. Previous approaches primarily focus on individual tasks, making it difficult to assess the complete data science workflow. Moreover, they struggle to handle real-time changes in intermediate data and fail to adapt dynamically to evolving task dependencies inherent to data science problems. In this paper, we present Data Interpreter, an LLM-based agent designed to automatically solve various data science problems end-to-end. Our Data Interpreter incorporates two key modules: 1) Hierarchical Graph Modeling, which breaks down complex problems into manageable subproblems, enabling dynamic node generation and graph optimization; and 2) Programmable Node Generation, a technique that refines and verifies each subproblem to iteratively improve code generation results and robustness. Extensive experiments consistently demonstrate the superiority of Data Interpreter. On InfiAgent-DABench, it achieves a 25% performance boost, raising accuracy from 75.9% to 94.9%. For machine learning and open-ended tasks, it improves performance from 88% to 95%, and from 60% to 97%, respectively. Moreover, on the MATH dataset, Data Interpreter achieves remarkable performance with a 26% improvement compared to state-of-the-art baselines. The code is available at https://github.com/geekan/MetaGPT.

Huayu Huang, Chen Chen, Banglei Guan et al.

Tracking and measuring targets using a variety of sensors mounted on UAVs is an effective means to quickly and accurately locate the target. This paper proposes a fusion localization method based on ridge estimation, combining the advantages of rich scene information from sequential imagery with the high precision of laser ranging to enhance localization accuracy. Under limited conditions such as long distances, small intersection angles, and large inclination angles, the column vectors of the design matrix have serious multicollinearity when using the least squares estimation algorithm. The multicollinearity will lead to ill-conditioned problems, resulting in significant instability and low robustness. Ridge estimation is introduced to mitigate the serious multicollinearity under the condition of limited observation. Experimental results demonstrate that our method achieves higher localization accuracy compared to ground localization algorithms based on single information. Moreover, the introduction of ridge estimation effectively enhances the robustness, particularly under limited observation conditions.

Zifan Chen, Xinyu Nan, Jiazheng Li et al.

Volumetric segmentation is important in medical imaging, but current methods face challenges like requiring lots of manual annotations and being tailored to specific tasks, which limits their versatility. General segmentation models used for natural images don't perform well with the unique features of medical images. There's a strong need for an adaptable approach that can effectively handle different 3D medical structures and imaging modalities. In this study, we present PAM (Propagating Anything Model), a segmentation approach that uses a 2D prompt, like a bounding box or sketch, to create a complete 3D segmentation of medical image volumes. PAM works by modeling relationships between slices, maintaining information flow across the 3D structure. It combines a CNN-based UNet for processing within slices and a Transformer-based attention module for propagating information between slices, leading to better generalizability across various imaging modalities. PAM significantly outperformed existing models like MedSAM and SegVol, with an average improvement of over 18.1% in dice similarity coefficient (DSC) across 44 medical datasets and various object types. It also showed stable performance despite prompt deviations and different propagation setups, and faster inference speeds compared to other models. PAM's one-view prompt design made it more efficient, reducing interaction time by about 63.6% compared to two-view prompts. Thanks to its focus on structural relationships, PAM handled unseen and complex objects well, showing a unique ability to generalize to new situations. PAM represents an advancement in medical image segmentation, effectively reducing the need for extensive manual work and specialized training. Its adaptability makes it a promising tool for more automated and reliable analysis in clinical settings.

Zhang Li, Yuliang Liu, Qiang Liu et al.

We introduce MonkeyOCR, a vision-language model for document parsing that advances the state of the art by leveraging a Structure-Recognition-Relation (SRR) triplet paradigm. This design simplifies what would otherwise be a complex multi-tool pipeline (as in MinerU's modular approach) and avoids the inefficiencies of processing full pages with giant end-to-end models (e.g., large multimodal LLMs like Qwen-VL). In SRR, document parsing is abstracted into three fundamental questions - "Where is it?" (structure), "What is it?" (recognition), and "How is it organized?" (relation) - corresponding to layout analysis, content identification, and logical ordering. This focused decomposition balances accuracy and speed: it enables efficient, scalable processing without sacrificing precision. To train and evaluate this approach, we introduce the MonkeyDoc (the most comprehensive document parsing dataset to date), with 3.9 million instances spanning over ten document types in both Chinese and English. Experiments show that MonkeyOCR outperforms MinerU by an average of 5.1%, with particularly notable improvements on challenging content such as formulas (+15.0%) and tables (+8.6%). Remarkably, our 3B-parameter model surpasses much larger and top-performing models, including Qwen2.5-VL (72B) and Gemini 2.5 Pro, achieving state-of-the-art average performance on English document parsing tasks. In addition, MonkeyOCR processes multi-page documents significantly faster (0.84 pages per second compared to 0.65 for MinerU and 0.12 for Qwen2.5-VL-7B). The 3B model can be efficiently deployed for inference on a single NVIDIA 3090 GPU. Code and models will be released at https://github.com/Yuliang-Liu/MonkeyOCR.

Yibin Ye, Xichao Teng, Shuo Chen et al.

Optical-SAR image matching is a fundamental task for image fusion and visual navigation. However, all large-scale open SAR dataset for methods development are collected from single platform, resulting in limited satellite types and spatial resolutions. Since images captured by different sensors vary significantly in both geometric and radiometric appearance, existing methods may fail to match corresponding regions containing the same content. Besides, most of existing datasets have not been categorized based on the characteristics of different scenes. To encourage the design of more general multi-modal image matching methods, we introduce a large-scale Multi-sources,Multi-resolutions, and Multi-scenes dataset for Optical-SAR image matching(3MOS). It consists of 155K optical-SAR image pairs, including SAR data from six commercial satellites, with resolutions ranging from 1.25m to 12.5m. The data has been classified into eight scenes including urban, rural, plains, hills, mountains, water, desert, and frozen earth. Extensively experiments show that none of state-of-the-art methods achieve consistently superior performance across different sources, resolutions and scenes. In addition, the distribution of data has a substantial impact on the matching capability of deep learning models, this proposes the domain adaptation challenge in optical-SAR image matching. Our data and code will be available at:https://github.com/3M-OS/3MOS.

Yurui Li, Yuxuan Chen, Li Zhang et al.

The significant role of division of labor (DOL) in promoting cooperation is widely recognized in real-world applications.Many cooperative multi-agent reinforcement learning (MARL) methods have incorporated the concept of DOL to improve cooperation among agents.However, the tasks used in existing testbeds typically correspond to tasks where DOL is often not a necessary feature for achieving optimal policies.Additionally, the full utilize of DOL concept in MARL methods remains unrealized due to the absence of appropriate tasks.To enhance the generality and applicability of MARL methods in real-world scenarios, there is a necessary to develop tasks that demand multi-agent DOL and cooperation.In this paper, we propose a series of tasks designed to meet these requirements, drawing on real-world rules as the guidance for their design.We guarantee that DOL and cooperation are necessary condition for completing tasks and introduce three factors to expand the diversity of proposed tasks to cover more realistic situations.We evaluate 10 cooperative MARL methods on the proposed tasks.The results indicate that all baselines perform poorly on these tasks.To further validate the solvability of these tasks, we also propose simplified variants of proposed tasks.Experimental results show that baselines are able to handle these simplified variants, providing evidence of the solvability of the proposed tasks.The source files is available at https://github.com/Yurui-Li/CTC.

Shuo Zhang, Biao Yang, Zhang Li et al.

While large multi-modal models (LMM) have shown notable progress in multi-modal tasks, their capabilities in tasks involving dense textual content remains to be fully explored. Dense text, which carries important information, is often found in documents, tables, and product descriptions. Understanding dense text enables us to obtain more accurate information, assisting in making better decisions. To further explore the capabilities of LMM in complex text tasks, we propose the DT-VQA dataset, with 170k question-answer pairs. In this paper, we conduct a comprehensive evaluation of GPT4V, Gemini, and various open-source LMMs on our dataset, revealing their strengths and weaknesses. Furthermore, we evaluate the effectiveness of two strategies for LMM: prompt engineering and downstream fine-tuning. We find that even with automatically labeled training datasets, significant improvements in model performance can be achieved. We hope that this research will promote the study of LMM in dense text tasks. Code will be released at https://github.com/Yuliang-Liu/MultimodalOCR.

Jiahui Zhang, Yurui Chen, Yueming Xu et al.

Leveraging diverse robotic data for pretraining remains a critical challenge. Existing methods typically model the dataset's action distribution using simple observations as inputs. However, these inputs are often incomplete, resulting in a dispersed conditional action distribution-an issue we refer to as coordinate system chaos and state chaos. This inconsistency significantly hampers pretraining efficiency. To address this, we propose 4D-VLA, a novel approach that effectively integrates 4D information into the input to mitigate these sources of chaos. Our model introduces depth and temporal information into visual features with sequential RGB-D inputs, aligning the coordinate systems of the robot and the scene. This alignment endows the model with strong spatiotemporal reasoning capabilities while minimizing training overhead. Additionally, we introduce memory bank sampling, a frame sampling strategy designed to extract informative frames from historical images, further improving effectiveness and efficiency. Experimental results demonstrate that our pretraining method and architectural components substantially enhance model performance. In both simulated and real-world experiments, our model achieves a significant increase in success rate over OpenVLA. To further assess spatial perception and generalization to novel views, we introduce MV-Bench, a multi-view simulation benchmark. Our model consistently outperforms existing methods, demonstrating stronger spatial understanding and adaptability.

Ming Nie, Xinyue Cai, Hang Xu et al.

Lane detection has evolved highly functional autonomous driving system to understand driving scenes even under complex environments. In this paper, we work towards developing a generalized computer vision system able to detect lanes without using any annotation. We make the following contributions: (i) We illustrate how to perform unsupervised 3D lane segmentation by leveraging the distinctive intensity of lanes on the LiDAR point cloud frames, and then obtain the noisy lane labels in the 2D plane by projecting the 3D points; (ii) We propose a novel self-supervised training scheme, dubbed LaneCorrect, that automatically corrects the lane label by learning geometric consistency and instance awareness from the adversarial augmentations; (iii) With the self-supervised pre-trained model, we distill to train a student network for arbitrary target lane (e.g., TuSimple) detection without any human labels; (iv) We thoroughly evaluate our self-supervised method on four major lane detection benchmarks (including TuSimple, CULane, CurveLanes and LLAMAS) and demonstrate excellent performance compared with existing supervised counterpart, whilst showing more effective results on alleviating the domain gap, i.e., training on CULane and test on TuSimple.

Yuang Wang, Siyeop Yoon, Pengfei Jin et al.

Diffusion-based models have demonstrated remarkable effectiveness in image restoration tasks; however, their iterative denoising process, which starts from Gaussian noise, often leads to slow inference speeds. The Image-to-Image Schrödinger Bridge (I$^2$SB) offers a promising alternative by initializing the generative process from corrupted images while leveraging training techniques from score-based diffusion models. In this paper, we introduce the Implicit Image-to-Image Schrödinger Bridge (I$^3$SB) to further accelerate the generative process of I$^2$SB. I$^3$SB restructures the generative process into a non-Markovian framework by incorporating the initial corrupted image at each generative step, effectively preserving and utilizing its information. To enable direct use of pretrained I$^2$SB models without additional training, we ensure consistency in marginal distributions. Extensive experiments across many image corruptions, including noise, low resolution, JPEG compression, and sparse sampling, and multiple image modalities, such as natural, human face, and medical images, demonstrate the acceleration benefits of I$^3$SB. Compared to I$^2$SB, I$^3$SB achieves the same perceptual quality with fewer generative steps, while maintaining or improving fidelity to the ground truth.

Yunlong Yuan, Yuanfan Guo, Chunwei Wang et al.

Recent advances in diffusion models have greatly improved text-driven video generation. However, training models for long video generation demands significant computational power and extensive data, leading most video diffusion models to be limited to a small number of frames. Existing training-free methods that attempt to generate long videos using pre-trained short video diffusion models often struggle with issues such as insufficient motion dynamics and degraded video fidelity. In this paper, we present Brick-Diffusion, a novel, training-free approach capable of generating long videos of arbitrary length. Our method introduces a brick-to-wall denoising strategy, where the latent is denoised in segments, with a stride applied in subsequent iterations. This process mimics the construction of a staggered brick wall, where each brick represents a denoised segment, enabling communication between frames and improving overall video quality. Through quantitative and qualitative evaluations, we demonstrate that Brick-Diffusion outperforms existing baseline methods in generating high-fidelity videos.

Ting Luo, Jing Zhang, Yingwei Qiu et al.

Emotion decoding using Electroencephalography (EEG)-based affective brain-computer interfaces (aBCIs) plays a crucial role in affective computing but is limited by challenges such as EEG's non-stationarity, individual variability, and the high cost of large labeled datasets. While deep learning methods are effective, they require extensive computational resources and large data volumes, limiting their practical application. To overcome these issues, we propose Manifold-based Domain Adaptation with Dynamic Distribution (M3D), a lightweight, non-deep transfer learning framework. M3D consists of four key modules: manifold feature transformation, dynamic distribution alignment, classifier learning, and ensemble learning. The data is mapped to an optimal Grassmann manifold space, enabling dynamic alignment of source and target domains. This alignment is designed to prioritize both marginal and conditional distributions, improving adaptation efficiency across diverse datasets. In classifier learning, the principle of structural risk minimization is applied to build robust classification models. Additionally, dynamic distribution alignment iteratively refines the classifier. The ensemble learning module aggregates classifiers from different optimization stages to leverage diversity and enhance prediction accuracy. M3D is evaluated on two EEG emotion recognition datasets using two validation protocols (cross-subject single-session and cross-subject cross-session) and a clinical EEG dataset for Major Depressive Disorder (MDD). Experimental results show that M3D outperforms traditional non-deep learning methods with a 4.47% average improvement and achieves deep learning-level performance with reduced data and computational requirements, demonstrating its potential for real-world aBCI applications.

Shunkun Liang, Dongcai Tan, Banglei Guan et al.

Visual navigation devices require precise calibration to achieve high-precision localization and navigation, which includes camera and attitude calibration. To address the limitations of time-consuming camera calibration and complex attitude adjustment processes, this study presents a collimator-based calibration method and system. Based on the optical characteristics of the collimator, a single-image camera calibration algorithm is introduced. In addition, integrated with the precision adjustment mechanism of the calibration frame, a rotation transfer model between coordinate systems enables efficient attitude calibration. Experimental results demonstrate that the proposed method achieves accuracy and stability comparable to traditional multi-image calibration techniques. Specifically, the re-projection errors are less than 0.1463 pixels, and average attitude angle errors are less than 0.0586 degrees with a standard deviation less than 0.0257 degrees, demonstrating high precision and robustness.

Jinghao Wang, Zhang Li, Zi Wang et al.

6D pose confidence region estimation has emerged as a critical direction, aiming to perform uncertainty quantification for assessing the reliability of estimated poses. However, current sampling-based approach suffers from critical limitations that severely impede their practical deployment: 1) the sampling speed significantly decreases as the number of samples increases. 2) the derived confidence regions are often excessively large. To address these challenges, we propose a deterministic and efficient method for estimating pose confidence regions. Our approach uses inductive conformal prediction to calibrate the deterministically regressed Gaussian keypoint distributions into 2D keypoint confidence regions. We then leverage the implicit function theorem to propagate these keypoint confidence regions directly into 6D pose confidence regions. This method avoids the inefficiency and inflated region sizes associated with sampling and ensembling. It provides compact confidence regions that cover the ground-truth poses with a user-defined confidence level. Experimental results on the LineMOD Occlusion and SPEED datasets show that our method achieves higher pose estimation accuracy with reduced computational time. For the same coverage rate, our method yields significantly smaller confidence region volumes, reducing them by up to 99.9\% for rotations and 99.8\% for translations. The code will be available soon.

Haofan Wu, Yin Huang, Yuqing Wu et al.

High-quality fundus images provide essential anatomical information for clinical screening and ophthalmic disease diagnosis. Yet, due to hardware limitations, operational variability, and patient compliance, fundus images often suffer from low resolution and signal-to-noise ratio. Recent years have witnessed promising progress in fundus image enhancement. However, existing works usually focus on restoring structural details or global characteristics of fundus images, lacking a unified image enhancement framework to recover comprehensive multi-scale information. Moreover, few methods pinpoint the target of image enhancement, e.g., lesions, which is crucial for medical image-based diagnosis. To address these challenges, we propose a multi-scale target-aware representation learning framework (MTRL-FIE) for efficient fundus image enhancement. Specifically, we propose a multi-scale feature encoder (MFE) that employs wavelet decomposition to embed both low-frequency structural information and high-frequency details. Next, we design a structure-preserving hierarchical decoder (SHD) to fuse multi-scale feature embeddings for real fundus image restoration. SHD integrates hierarchical fusion and group attention mechanisms to achieve adaptive feature fusion while retaining local structural smoothness. Meanwhile, a target-aware feature aggregation (TFA) module is used to enhance pathological regions and reduce artifacts. Experimental results on multiple fundus image datasets demonstrate the effectiveness and generalizability of MTRL-FIE for fundus image enhancement. Compared to state-of-the-art methods, MTRL-FIE achieves superior enhancement performance with a more lightweight architecture. Furthermore, our approach generalizes to other ophthalmic image processing tasks without supervised fine-tuning, highlighting its potential for clinical applications.

Yuang Wang, Siyeop Yoon, Rui Hu et al.

Improving the spatial resolution of CT images is a meaningful yet challenging task, often accompanied by the issue of noise amplification. This article introduces an innovative framework for noise-controlled CT super-resolution utilizing the conditional diffusion model. The model is trained on hybrid datasets, combining noise-matched simulation data with segmented details from real data. Experimental results with real CT images validate the effectiveness of our proposed framework, showing its potential for practical applications in CT imaging.

Zhang Li, Jiehua Zhang, Tao Tan et al.

Accurate segmentation of lung cancer in pathology slides is a critical step in improving patient care. We proposed the ACDC@LungHP (Automatic Cancer Detection and Classification in Whole-slide Lung Histopathology) challenge for evaluating different computer-aided diagnosis (CADs) methods on the automatic diagnosis of lung cancer. The ACDC@LungHP 2019 focused on segmentation (pixel-wise detection) of cancer tissue in whole slide imaging (WSI), using an annotated dataset of 150 training images and 50 test images from 200 patients. This paper reviews this challenge and summarizes the top 10 submitted methods for lung cancer segmentation. All methods were evaluated using the false positive rate, false negative rate, and DICE coefficient (DC). The DC ranged from 0.7354$\pm$0.1149 to 0.8372$\pm$0.0858. The DC of the best method was close to the inter-observer agreement (0.8398$\pm$0.0890). All methods were based on deep learning and categorized into two groups: multi-model method and single model method. In general, multi-model methods were significantly better ($\textit{p}$<$0.01$) than single model methods, with mean DC of 0.7966 and 0.7544, respectively. Deep learning based methods could potentially help pathologists find suspicious regions for further analysis of lung cancer in WSI.

Banglei Guan, Ji Zhao, Zhang Li et al.

In this paper we present four cases of minimal solutions for two-view relative pose estimation by exploiting the affine transformation between feature points and we demonstrate efficient solvers for these cases. It is shown, that under the planar motion assumption or with knowledge of a vertical direction, a single affine correspondence is sufficient to recover the relative camera pose. The four cases considered are two-view planar relative motion for calibrated cameras as a closed-form and a least-squares solution, a closed-form solution for unknown focal length and the case of a known vertical direction. These algorithms can be used efficiently for outlier detection within a RANSAC loop and for initial motion estimation. All the methods are evaluated on both synthetic data and real-world datasets from the KITTI benchmark. The experimental results demonstrate that our methods outperform comparable state-of-the-art methods in accuracy with the benefit of a reduced number of needed RANSAC iterations.

Li Deng, Shuo Zhang, Krisztian Balog

Tables contain valuable knowledge in a structured form. We employ neural language modeling approaches to embed tabular data into vector spaces. Specifically, we consider different table elements, such caption, column headings, and cells, for training word and entity embeddings. These embeddings are then utilized in three particular table-related tasks, row population, column population, and table retrieval, by incorporating them into existing retrieval models as additional semantic similarity signals. Evaluation results show that table embeddings can significantly improve upon the performance of state-of-the-art baselines.

Zhang Li, Zheyu Hu, Jiaolong Xu et al.

Aim: Early detection and correct diagnosis of lung cancer are the most important steps in improving patient outcome. This study aims to assess which deep learning models perform best in lung cancer diagnosis. Methods: Non-small cell lung carcinoma and small cell lung carcinoma biopsy specimens were consecutively obtained and stained. The specimen slides were diagnosed by two experienced pathologists (over 20 years). Several deep learning models were trained to discriminate cancer and non-cancer biopsies. Result: Deep learning models give reasonable AUC from 0.8810 to 0.9119. Conclusion: The deep learning analysis could help to speed up the detection process for the whole-slide image (WSI) and keep the comparable detection rate with human observer.

Tao Tan, Zhang Li, Haixia Liu et al.

Bronchoscopy inspection as a follow-up procedure from the radiological imaging plays a key role in lung disease diagnosis and determining treatment plans for the patients. Doctors needs to make a decision whether to biopsy the patients timely when performing bronchoscopy. However, the doctors also needs to be very selective with biopsies as biopsies may cause uncontrollable bleeding of the lung tissue which is life-threaten. To help doctors to be more selective on biopsies and provide a second opinion on diagnosis, in this work, we propose a computer-aided diagnosis (CAD) system for lung diseases including cancers and tuberculosis (TB). The system is developed based on transfer learning. We propose a novel transfer learning method: sentential fine-tuning . Compared to traditional fine-tuning methods, our methods achieves the best performance. We obtained a overall accuracy of 77.0% a dataset of 81 normal cases, 76 tuberculosis cases and 277 lung cancer cases while the other traditional transfer learning methods achieve an accuracy of 73% and 68%. . The detection accuracy of our method for cancers, TB and normal cases are 87%, 54% and 91% respectively. This indicates that the CAD system has potential to improve lung disease diagnosis accuracy in bronchoscopy and it also might be used to be more selective with biopsies.