arXiv subjects

Jiapan Guo

Publications and source records attributed to Jiapan Guo.

11 recordsLinked to original sources

arXiv2026

Beyond Instrument Motion: Recognizing Tissue Tension Toward Surgical Skill Assessment

Surgical performance assessment in minimally invasive surgery largely relies on manual expert review, making it time-consuming, subjective, and difficult to scale. While existing surgical video understanding methods address tasks such as instrument segmentation, surgical phase recognition, and action recognition, they do not explicitly capture fine-grained tissue handling, a key indicator of surgical quality. To address this gap, we introduce tissue tension recognition, a new clinically motivated video understanding task for laparoscopic and robot-assisted rectal cancer surgery. To support this task, we construct SurgTension, the first expert-annotated tissue tension dataset, providing a benchmark for objective tissue tension recognition. We further propose TensionTRAC, a lightweight trajectory-based framework that models tissue tension from sparse point trajectories. Using a compact trajectory encoder, TensionTRAC achieves competitive performance against strong pretrained video backbones.

cs.CV↗

arXiv2026

Uncertainty Identifies Difficult Samples Across Methods: A Multi-Task Study on a Heterogeneous Skin Lesion Dataset

Skin lesion classifiers can be confidently wrong on the cases that matter most, so knowing when a prediction should not be trusted is clinically as useful as the prediction. We study uncertainty quantification on a dataset pooled from many ISIC sources, with a shared backbone and two jointly learned heads: a binary malignant versus non-malignant head and a five-class diagnostic head. Five UQ methods (MC Dropout, DropConnect, Flipout, Deep Ensembles, DUQ) are compared on accuracy, calibration, uncertainty decomposition, and risk-coverage. Difficulty is largely method-agnostic: even methods with narrow entropy distributions rank the same samples as hard (per-sample entropy correlations of $0.54$ to $0.91$). The choice of method matters more for calibration and uncertainty decomposition, where Deep Ensembles is the clear winner, than for finding difficult cases. The ranking is also good enough that deferring the most uncertain cases removes a disproportionate share of errors, supporting uncertainty-based selective referral, evaluated here in-distribution only.

cs.CV↗

arXiv2026

Improving Automatic Speech Recognition for Speakers Treated for Oral Cancer using Data Augmentation and LLM Error Correction

In recent years, the performance of automatic speech recognition (ASR) systems has made considerable progress. Unfortunately, for people with speech impairments, such as people treated for oral cancer (OC), ASR performance is still lagging behind. The scarcity and variability of OC speech data makes development of ASR models for this type of speech difficult. In this work, we use data augmentation and large language model (LLM) error correction to mitigate this problem. We apply various augmentation techniques on a corpus of Dutch oral cancer speech to create synthetic data, and evaluate their effect on ASR performance. We finetune Whisper and Massively Multilingual Speech (MMS) models for each augmentation technique and observe, on average, an 8% relative decrease in Word Error Rate (WER) when including data created using text-to-speech (TTS). When employing LLMs for error correction, we see a further 21.4-26.2% relative decrease in WER for finetuned ASR models and a 10.0% relative decrease for non-finetuned models. Overall, we achieve a 40% relative WER decrease for Whisper and a 50% relative WER decrease for MMS, indicating that a combination of data augmentation and LLM correction is a viable strategy for the recognition of OC speech.

eess.AS↗

arXiv2026

Meningioma Analysis and Diagnosis using Limited Labeled Samples

The biological behavior and treatment response of meningiomas depend on their grade, making an accurate diagnosis essential for treatment planning and prognosis assessment. We observed that the weighted fusion of spatial-frequency domain features significantly influences meningioma classification performance. Notably, the contribution of specific frequency bands obtained by discrete wavelet transform varies considerably across different images. A feature fusion architecture with adaptive weights of different frequency band information and spatial domain information is proposed for few-shot meningioma learning. To verify the effectiveness of the proposed method, a new MRI dataset of meningiomas is introduced. The experimental results demonstrate the superiority of the proposed method compared with existing state-of-the-art methods in three datasets. The code will be available at: https://github.com/ICL-SUST/AMSF-Net

cs.CV↗

arXiv2026

Deep learning-based neurodevelopmental assessment in preterm infants

Preterm infants (born between 28 and 37 weeks of gestation) face elevated risks of neurodevelopmental delays, making early identification crucial for timely intervention. While deep learning-based volumetric segmentation of brain MRI scans offers a promising avenue for assessing neonatal neurodevelopment, achieving accurate segmentation of white matter (WM) and gray matter (GM) in preterm infants remains challenging due to their comparable signal intensities (isointense appearance) on MRI during early brain development. To address this, we propose a novel segmentation neural network, named Hierarchical Dense Attention Network. Our architecture incorporates a 3D spatial-channel attention mechanism combined with an attention-guided dense upsampling strategy to enhance feature discrimination in low-contrast volumetric data. Quantitative experiments demonstrate that our method achieves superior segmentation performance compared to state-of-the-art baselines, effectively tackling the challenge of isointense tissue differentiation. Furthermore, application of our algorithm confirms that WM and GM volumes in preterm infants are significantly lower than those in term infants, providing additional imaging evidence of the neurodevelopmental delays associated with preterm birth. The code is available at: https://github.com/ICL-SUST/HDAN.

cs.CV↗

arXiv2025

Gotta catch 'em all! Towards File Localisation from Issues at Large

Bug localisation, the study of developing methods to localise the files requiring changes to resolve bugs, has been researched for a long time to develop methods capable of saving developers' time. Recently, researchers are starting to consider issues outside of bugs. Nevertheless, most existing research into file localisation from issues focusses on bugs or uses other selection methods to ensure only certain types of issues are considered as part of the focus of the work. Our goal is to work on all issues at large, without any specific selection. In this work, we provide a data pipeline for the creation of issue file localisation datasets, capable of dealing with arbitrary branching and merging practices. We provide a baseline performance evaluation for the file localisation problem using traditional information retrieval approaches. Finally, we use statistical analysis to investigate the influence of biases known in the bug localisation community on our dataset. Our results show that methods designed using bug-specific heuristics perform poorly on general issue types, indicating a need for research into general purpose models. Furthermore, we find that there are small, but statistically significant differences in performance between different issue types. Finally, we find that the presence of identifiers have a small effect on performance for most issue types. Many results are project-dependent, encouraging the development of methods which can be tuned to project-specific characteristics.

cs.SE↗

arXiv2025

Feature Complementation Architecture for Visual Place Recognition

Visual place recognition (VPR) plays a crucial role in robotic localization and navigation. The key challenge lies in constructing feature representations that are robust to environmental changes. Existing methods typically adopt convolutional neural networks (CNNs) or vision Transformers (ViTs) as feature extractors. However, these architectures excel in different aspects -- CNNs are effective at capturing local details. At the same time, ViTs are better suited for modeling global context, making it difficult to leverage the strengths of both. To address this issue, we propose a local-global feature complementation network (LGCN) for VPR which integrates a parallel CNN-ViT hybrid architecture with a dynamic feature fusion module (DFM). The DFM performs dynamic feature fusion through joint modeling of spatial and channel-wise dependencies. Furthermore, to enhance the expressiveness and adaptability of the ViT branch for VPR tasks, we introduce lightweight frequency-to-spatial fusion adapters into the frozen ViT backbone. These adapters enable task-specific adaptation with controlled parameter overhead. Extensive experiments on multiple VPR benchmark datasets demonstrate that the proposed LGCN consistently outperforms existing approaches in terms of localization accuracy and robustness, validating its effectiveness and generalizability.

cs.CV↗

arXiv2023

Second-order Anisotropic Gaussian Directional Derivative Filters for Blob Detection

Interest point detection methods have received increasing attention and are widely used in computer vision tasks such as image retrieval and 3D reconstruction. In this work, second-order anisotropic Gaussian directional derivative filters with multiple scales are used to smooth the input image and a novel blob detection method is proposed. Extensive experiments demonstrate the superiority of our proposed method over state-of-the-art benchmarks in terms of detection performance and robustness to affine transformations.

cs.CV↗

arXiv2020

Recurrent convolutional neural networks for mandible segmentation from computed tomography

Recently, accurate mandible segmentation in CT scans based on deep learning methods has attracted much attention. However, there still exist two major challenges, namely, metal artifacts among mandibles and large variations in shape or size among individuals. To address these two challenges, we propose a recurrent segmentation convolutional neural network (RSegCNN) that embeds segmentation convolutional neural network (SegCNN) into the recurrent neural network (RNN) for robust and accurate segmentation of the mandible. Such a design of the system takes into account the similarity and continuity of the mandible shapes captured in adjacent image slices in CT scans. The RSegCNN infers the mandible information based on the recurrent structure with the embedded encoder-decoder segmentation (SegCNN) components. The recurrent structure guides the system to exploit relevant and important information from adjacent slices, while the SegCNN component focuses on the mandible shapes from a single CT slice. We conducted extensive experiments to evaluate the proposed RSegCNN on two head and neck CT datasets. The experimental results show that the RSegCNN is significantly better than the state-of-the-art models for accurate mandible segmentation.

eess.IV↗

arXiv2019

Automatic Pulmonary Nodule Detection in CT Scans Using Convolutional Neural Networks Based on Maximum Intensity Projection

Accurate pulmonary nodule detection is a crucial step in lung cancer screening. Computer-aided detection (CAD) systems are not routinely used by radiologists for pulmonary nodule detection in clinical practice despite their potential benefits. Maximum intensity projection (MIP) images improve the detection of pulmonary nodules in radiological evaluation with computed tomography (CT) scans. Inspired by the clinical methodology of radiologists, we aim to explore the feasibility of applying MIP images to improve the effectiveness of automatic lung nodule detection using convolutional neural networks (CNNs). We propose a CNN-based approach that takes MIP images of different slab thicknesses (5 mm, 10 mm, 15 mm) and 1 mm axial section slices as input. Such an approach augments the two-dimensional (2-D) CT slice images with more representative spatial information that helps discriminate nodules from vessels through their morphologies. Our proposed method achieves sensitivity of 92.67% with 1 false positive per scan and sensitivity of 94.19% with 2 false positives per scan for lung nodule detection on 888 scans in the LIDC-IDRI dataset. The use of thick MIP images helps the detection of small pulmonary nodules (3 mm-10 mm) and results in fewer false positives. Experimental results show that utilizing MIP images can increase the sensitivity and lower the number of false positives, which demonstrates the effectiveness and significance of the proposed MIP-based CNNs framework for automatic pulmonary nodule detection in CT scans. The proposed method also shows the potential that CNNs could gain benefits for nodule detection by combining the clinical procedure.

cs.CV↗

arXiv2018

3D segmentation of mandible from multisectional CT scans by convolutional neural networks

Segmentation of mandibles in CT scans during virtual surgical planning is crucial for 3D surgical planning in order to obtain a detailed surface representation of the patients bone. Automatic segmentation of mandibles in CT scans is a challenging task due to large variation in their shape and size between individuals. In order to address this challenge we propose a convolutional neural network approach for mandible segmentation in CT scans by considering the continuum of anatomical structures through different planes. The proposed convolutional neural network adopts the architecture of the U-Net and then combines the resulting 2D segmentations from three different planes into a 3D segmentation. We implement such a segmentation approach on 11 neck CT scans and then evaluate the performance. We achieve an average dice coefficient of $ 0.89 $ on two testing mandible segmentation. Experimental results show that our proposed approach for mandible segmentation in CT scans exhibits high accuracy.

cs.CV↗