Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Meng Zhou
About me
Page not in menu
This is a page not in th emain menu
Posts
记最强大脑第八季最终轮线下测试
Published:
前言
Machine Learning / Algorithm Engineer Interview Question (Chinese)
Published:
暑期即将告一段落，我暑期算法工程师实习也顺利结束了。在面试过程中面过不少公司，大多数都为技术面试。我总结了我所有遇到过的面试题供大家参考。面试职位大多数都是机器学习方向的算法工程师，绝大多数知识点都是和ML相关的。
portfolio
Optimizing Convolutional Neural Networks Hyperparameters using Genetic Algorithm
We develop a new optimization framework, genetic-based evolutionary strategy, to optimize the convolutional neural networks architecture for the Chest X-Ray classification task.
Image Editor Toolkit
We develop a image editor toolkit based on purely numpy that supports basic image manipulations.
Multitask Learning for Brain Tumor Segmentation using Transformer
We present MTSegFormer, a learning framework for 2D brain tumor segmentation using latent transformer through the Multi-task learning paradigm.
Shoulder Implant X-Ray Manufacturer Classification
In this paper, we compared the performance of various deep models, ranging from traditional machine learning methods, CNN-based deep learning methods to the modern state-of-the-art Vision Transformer (ViT) model. The results have showen that ViTs achieved a decent performance in X-Ray classification task, and transfer learning improved ViT by a large margin.
Predicting cuisine category using recipe ingredients
Use recipe ingredients to categorize the cuisine through machine learning and deep learning models.
publications
Domain Transfer Through Image-to-Image Translation in Prostate Cancer Detection
Abstract, 20th Annual Symposium of the Imaging Network of Ontario (ImNO), 2022
In this paper, we have presented a novel approach for unpaired image-to-image translation of prostate mp-MRI for classifying clinically significant PCa, to be applied in data-constrained settings. First, we introduce domain transfer, a novel pipeline to translate unpaired 3.0T multi-parametric prostate MRIs to 1.5T, to increase the number of training data. Second, we estimate the uncertainty of our models through an evidential deep learning approach; and leverage the dataset filtering technique during the training process. Furthermore, we introduce a simple, yet efficient Evidential Focal Loss that incorporates the focal loss with evidential uncertainty to train our model. Experiments have shown the superior performance of the proposed approach.
Download here
Truncated LinUCB for Stochastic Linear Bandits
Under Review, Electronic Journal of Statistics , 2022
We consider contextual bandits with a finite number of arms, where the contexts are independent and identically distributed d-dimensional random vectors, and the expected rewards are linear in both the arm parameters and contexts. We propose a truncated version of LinUCB and termed “Tr-LinUCB”, which follows LinUCB up to a truncation time S and performs pure exploitation afterwards. The Tr-LinUCB algorithm is shown to achieve O(dlog(T)) regret if S=Cdlog(T) for a sufficiently large constant C, and a matching lower bound is established, which shows the rate optimality of Tr-LinUCB in both d and T under a low dimensional regime.
Download here
An Attention-based Multi-Scale Feature Learning Network for Multimodal Medical Image Fusion
Arxiv, 2022
In this paper, we introduce a novel Dilated Residual Attention Network for the medical image fusion task to synthesize complementary information from multimodal medical images (CT and MRI) into a single image. Our network is capable to extract multi-scale deep semantic features. Furthermore, we propose a novel fixed fusion strategy termed Softmax-based weighted strategy based on the Softmax weights and matrix nuclear norm. Extensive experiments show our proposed network and fusion strategy exceed the state-of-the-art performance compared with reference image fusion methods on four commonly used fusion metrics.
Download here
Conditional Generation of 3D Brain Tumor Regions via VQGAN and Temporal-Agnostic Masked Transformer
International Conference on Medical Imaging with Deep Learning, 2024
In this paper, we present a class-conditioned ROI generation framework that combines a conditional vector-quantization GAN and a class-conditioned masked Transformer to generate high-resolution and diverse 3D brain tumor ROIs. We also propose a temporal-agnostic masking strategy to effectively learn relationships between semantic tokens in the latent space. Our experiments demonstrate that the proposed method can generate high-quality 3D MRIs of brain tumor regions for both low- and high-grade glioma (LGG/HGG) in the BraTS 2019 dataset.
Download here
Generating 3D Brain Tumor Regions in MRI using Vector-Quantization Generative Adversarial Networks
Computers in Biology and Medicine, 2024
In this work, we present a novel framework that uses vector-quantization GAN and a transformer incorporating masked token modeling to generate high-resolution and diverse 3D brain tumor ROIs that can be directly used as augmented data for the classification of brain tumor ROI. We apply our method to two imbalanced datasets where we augment the minority class: (1) the Multimodal Brain Tumor Segmentation Challenge (BraTS) 2019 dataset to generate new low-grade glioma (LGG) ROIs to balance with high-grade glioma (HGG) class; (2) the internal pediatric LGG (pLGG) dataset tumor ROIs with BRAF V600E Mutation genetic marker to balance with BRAF Fusion genetic marker class. We show that the proposed method outperforms various baseline models in both qualitative and quantitative measurements.
Download here
Edge-Enhanced Dilated Residual Attention Network for Multimodal Medical Image Fusion
IEEE International Conference on Bioinformatics and Biomedicine, 2024
In this paper, we propose a novel CNN-based architecture with a Dilated Residual Attention Network Module for effective multiscale feature extraction, coupled with a gradient operator to enhance edge detail learning. To ensure fast and efficient fusion, we present a parameter-free fusion strategy based on the weighted nuclear norm of softmax, which requires no additional computations during training or inference. Extensive experiments on MRI-CT, MRI-SPECT, and a downstream brain tumor classification task demonstrate that our approach outperforms various baseline methods in terms of visual quality, texture preservation, and fusion speed, making it a possible practical solution for real-world clinical applications.
Download here
ClinicalFMamba: Mamba-based Multimodal Medical Image Fusion for Enhanced Clinical Diagnosis
International Conference on Machine Learning NewInML Workshop, 2025
In this work, we propose ClinicalFMamba, a novel end-to-end CNN-Mamba hybrid architecture that synergistically combines local and global feature modeling. Our approach introduces: Dilated Gated Convolution Blocks for hierarchical multiscale feature extraction, and a latent Mamba module that efficiently captures long-range spatial dependencies between feature regions and enabling cross-modal fusion in latent space. Comprehensive evaluations on three datasets demonstrate the superior fusion performance across multiple quantitative metrics while achieving real-time fusion. Notably, we validate the clinical utility of our approach on the downstream brain tumor classification, achieving up to 7% improvements on the AUC score. Our method establishes a new paradigm for efficient multimodal medical image fusion suitable for real-time clinical deployment.
Download here
ClinicalFMamba: Advancing Clinical Assessment using Mamba-based Multimodal Neuroimaging Fusion
International Conference on Machine Learning in Medical Imaging, held in conjunction with MICCAI, 2025
In this work, we propose ClinicalFMamba, a novel end-to-end CNN-Mamba hybrid architecture that synergistically combines local and global feature modeling for 2D and 3D images. We further design a tri-plane scanning strategy for effectively learning volumetric dependencies in 3D images. Comprehensive evaluations on three datasets demonstrate the superior fusion performance across multiple quantitative metrics while achieving real-time fusion. We further validate the clinical utility of our approach on downstream 2D/3D brain tumor classification tasks, achieving superior performance over baseline methods. Our method establishes a new paradigm for efficient multimodal medical image fusion suitable for real-time clinical deployment.
Download here
talks
Towards Domain Translation in Prostate Cancer Detection
Published:
Poster Presentation at Vector Institute Research Symposium. We take the 3.0T MRI images from the “ProstateX” challenge; translate to 1.5T-like MRI images based on the Cycle-GAN framework; and train a 3D Convolutional Neural Network for Prostate Cancer classification on translated images for the local use. Poster booklet link.
Domain Transer through Image-to-Image translation in Prostate Cancer Detection
Published:
Pitch-and-Poster Presentation at the 2022 Imaging Network Ontario Symposium. ImNO 2022 Program booklet link.
Edge-Enhanced Dilated Residual Attention Network for Multimodal Medical Image Fusion
Published:
Oral presentation on our short paper.
teaching
CISC 221
Undergraduate course, Queen's University, School of Computing, 2019
TA for CISC221 Computer Architetcure for 2019 Fall and 2022 Winter, a core second-year CS course for all CS-related majors. I managed a group of 20+ students, helped them with assignments, labs, held test reviews and marked assignments and tests. Course info is available at here.
MATH 110/121
Undergraduate course, Queen's University, Department of Mathematics and Statistics, 2020
TA for first-year core Math course MATH 110 Linear Algebra and MATH 121 Differential and Integral Calculus 2020 Fall & 2021 Winter. Held weekly office hour talking about assignments and course materials. Course info is available at here
CISC/CMPE 457
Undergraduate course, Queen's University, School of Computing, 2021
TA for the fourth-year CISC/CMPE 457 2021 Fall, Image Processing and Computer Vision. I managed a group of 20 students, helped them with assignment, provided test reviews and marked assignments using Python and Linux. I am the only undergrad TA for this course for Fall 2021. Course info is available at here.
STAT 457/857
Undergraduate/Graduate joint course, Queen's University, Department of Mathematics and Statistics, 2022
TA for fourth-year STAT 457/857 Statistical Learning II course, 2022 Fall. I designed and prepared the midterm and final project using Python and R Programming Language, deployed to the Kaggle platform for students to participate. Course info is available at here.
CSC 108
Undergraduate course, University of Toronto, Department of Computer Science, 2022
TA for the first-year Computer Science course CSC108 Intro to Programming (Python) in 2022 Fall, 2023 Winter and 2023 Fall. Held weekly office hour to help students with their class exercises, home assignments, tests review and marked midterm and final exam. Course info is available at here.