A5037208015- Radiomics and Machine Learning in Medical Imaging
- Fuzzy Logic and Control Systems
- Complex Network Analysis Techniques
- Advanced Radiotherapy Techniques
- Lung Cancer Diagnosis and Treatment
- EEG and Brain-Computer Interfaces
- Evaluation Methods in Various Fields
- Neural Networks and Applications
- Advanced Computational Techniques and Applications
- Geomechanics and Mining Engineering
- Gastric Cancer Management and Outcomes
- Machine Learning and ELM
- Advanced Algorithms and Applications
- Regional Economic and Spatial Analysis
- Simulation and Modeling Applications
- Bioinformatics and Genomic Networks
- AI in cancer detection
- Rough Sets and Fuzzy Logic
- Imbalanced Data Classification Techniques
- Advanced Decision-Making Techniques
- Civil and Geotechnical Engineering Research
- Head and Neck Cancer Studies
- Geotechnical Engineering and Analysis
- Effects of Radiation Exposure
- Brain Tumor Detection and Classification
Hong Kong Polytechnic University
2022-2025
Jiangsu University of Science and Technology
2015-2024
Xi'an University of Science and Technology
2024
Chifeng University
2024
Jiangnan University
2016-2023
Tongji University
2021
Ningbo University
2015
Fudan University
2014-2015
Key Laboratory of Nuclear Radiation and Nuclear Energy Technology
2015
Nanjing University of Science and Technology
2015
Although Takagi-Sugeno-Kang (TSK) fuzzy classifier has been applied to a wide range of practical scenarios, how enhance its classification accuracy and interpretability simultaneously is still challenging task. In this paper, based on the powerful stacked generalization principle, deep TSK (D-TSK-FC) proposed achieve enhanced triplely concise for rules. D-TSK-FC consists base-building units. Just like existing popular learning, can be built in layer-by-layer way. terms training set plus...
To investigate the role of different multi-organ omics-based prediction models for pre-treatment Adaptive Radiotherapy (ART) eligibility in patients with nasopharyngeal carcinoma (NPC).Pre-treatment contrast-enhanced computed tomographic and magnetic resonance images, radiotherapy dose contour data 135 NPC treated at Hong Kong Queen Elizabeth Hospital were retrospectively analyzed extraction multi-omics features, namely Radiomics (R), Morphology (M), Dosiomics (D), Contouromics (C), from a...
The study aimed to predict acute radiation esophagitis (ARE) with grade ≥ 2 for patients locally advanced lung cancer (LALC) treated intensity-modulated therapy (IMRT) using multi-omics features, including radiomics and dosiomics.161 stage IIIA-IIIB LALC who received chemoradiotherapy (CRT) or radiotherapy by IMRT a prescribed dose from 45 70 Gy 2015 2019 were enrolled retrospectively. All the toxicity gradings given following Common Terminology Criteria Adverse Events V4.0. Multi-omics...
Interpretable artificial intelligence (AI), also known as explainable AI, is indispensable in establishing trustable AI for bench-to-bedside translation, with substantial implications human well-being. However, the majority of existing research this area has centered on designing complex and sophisticated methods, regardless their interpretability. Consequently, main prerequisite implementing trustworthy medical domains not been met. Scientists have developed various explanation methods...
Low temperature oxidation of coal is the nature with oxygen molecules at temperatures below its critical point or ignition point, usually from ambient to about 200°C. Air leakage and uneven distribution significantly impact spontaneous combustion in goaf. Understanding changes free radicals functional groups during low-temperature under different concentrations crucial for preventing controlling residual self-ignition. This study employs Fourier transform infrared spectroscopy analyze...
Existing research reveals that the misclassification rate for imbalanced data depends heavily on problematic areas due to existence of small disjoints, class overlap, borderline, and rare samples. In this study, by stacking zero-order Takagi-Sugeno-Kang (TSK) fuzzy subclassifiers minority its in deep ensemble, a novel deep-ensemble-level-based TSK classifier (IDE-TSK-FC) classification tasks is presented achieve both promising performance high interpretability classifiers. Simultaneously,...
Brain networks are commonly used to identify cognitive neurobehavioral and brain conscious disorders. Most of the studies on state focus characterization expression resting-state networks, but there few dynamic networks. In fact, analysis can find more valuable information, because it dynamically depict characteristics from time dimension. However, too much consideration will naturally hide many its static characteristics. Therefore, this study proposes a tense-based multi-view fusion fuzzy...
Abstract Radiomic model reliability is a central premise for its clinical translation. Presently, it assessed using test–retest or external data, which, unfortunately, often scarce in reality. Therefore, we aimed to develop novel image perturbation-based method (IPBM) the first of kind toward building reliable radiomic model. We developed prognostic head-and-neck cancer patients on training (70%) and evaluated testing (30%) cohort C-index. Subsequently, applied IPBM CT images both cohorts...
Using high robust radiomic features in modeling is recommended, yet its impact on model unclear. This study evaluated the model's robustness and generalizability after screening out low-robust before modeling. The results were validated with four datasets two clinically relevant tasks.A total of 1,419 head-and-neck cancer patients' computed tomography images, gross tumor volume segmentation, outcomes (distant metastasis local-regional recurrence) collected from publicly available datasets....
In this paper, we propose a blockwise combination of interpretable Takagi-Sugeno-Kang (TSK) fuzzy classifiers to simultaneously achieve high accuracy and concise interpretability. As special hierarchical classifier, the proposed classifier is built in stacked block-by-block way. Each base building block consists multiple zero-order TSK classifiers, which are trained an analytical manner by using negative correlation learning enhance generalization ability block. For utilizing principle,...
Significant lymph node shrinkage is common in patients with nasopharyngeal carcinoma (NPC) throughout radiotherapy (RT) treatment, causing ill-fitted thermoplastic masks (IfTMs). To deal this, an ad hoc adaptive (ART) may be required to ensure accurate and safe radiation delivery maintain treatment efficacy. Presently, the entire procedure for evaluating eligible ART candidate time-consuming, resource-demanding, highly inefficient. In artificial intelligence paradigm, pre-treatment...
Purpose: To evaluate the effectiveness of features obtained from our proposed incremental-dose-interval-based lung subregion segmentation (IDLSS) for predicting grade ≥ 2 acute radiation pneumonitis (ARP) in cancer patients upon intensity-modulated radiotherapy (IMRT). (1) Materials and Methods: A total 126 non-small-cell treated with IMRT were retrospectively analyzed. Five subregions (SRs) generated by intersection whole (WL) five sub-regions receiving incremental dose intervals. 4610...
Abstract Objective This study aimed to develop a prediction model for esophageal fistula (EF) in cancer (EC) patients treated with intensity-modulated radiation therapy (IMRT), by integrating multi-omics features from multiple volumes of interest (VOIs). Methods We retrospectively analyzed pretreatment planning computed tomographic (CT) images, three-dimensional dose distributions, and clinical factors 287 EC patients. Nine groups different combination omics [Radiomics (R), Dosiomics (D), RD...
In this paper, a new stacked-structure-based hierarchical Takagi-Sugeno-Kang (TSK) fuzzy classifier called SHFA-TSK-FC with both promising performance and high interpretability is proposed to tackle the shortcoming of existing classifiers in interpreting outputs rules intermediate layers. order achieve enhanced classification performance, each component unit, which zero-order TSK classifier, organized stacked way such that all input features original training samples plus interpretable...
Due to the existence of noise and/or uncertainty in available sleep-wake stage data, recognition stages with an efficient feature extraction has been facing following challenges: (1) how handle these uncertainties; (2) have interpretable recognition; (3) make good testing performance (i.e., generalization capability). To circumvent three challenges, a deep Takagi-Sugeno-Kang (TSK) fuzzy classifier random rule heritage called Drrh-TSK-FC is proposed for by integrating enhanced capability...
Abstract Background The immunohistochemical test (IHC) of HER2 and HR can provide prognostic information treatment guidance for invasive breast cancer patients. We aimed to develop noninvasive image signatures IS HR, respectively. independently evaluate their repeatability, reproducibility, association with pathological complete response (pCR) neoadjuvant chemotherapy. Methods Pre-treatment DWI, IHC receptor status HER2/HR, pCR chemotherapy 222 patients from the multi-institutional ACRIN...
The diagnosis of chronic thromboembolic pulmonary hypertension (CTEPH) is challenging due to nonspecific early symptoms, complex diagnostic processes, and small lesion sizes. This study aims develop an automatic method for CTEPH using non-contrasted computed tomography (NCCT) scans, enabling automated without precise annotation.