Hui Lin

Hui Lin, Tom Liu, Aggelos Katsaggelos et al.

Coronary angiography continues to serve as the primary method for diagnosing coronary artery disease (CAD), which is the leading global cause of mortality. The severity of CAD is quantified by the location, degree of narrowing (stenosis), and number of arteries involved. In current practice, this quantification is performed manually using visual inspection and thus suffers from poor inter- and intra-rater reliability. The MICCAI grand challenge: Automatic Region-based Coronary Artery Disease diagnostics using the X-ray angiography imagEs (ARCADE) curated a dataset with stenosis annotations, with the goal of creating an automated stenosis detection algorithm. Using a combination of machine learning and other computer vision techniques, we propose the architecture and algorithm StenUNet to accurately detect stenosis from X-ray Coronary Angiography. Our submission to the ARCADE challenge placed 3rd among all teams. We achieved an F1 score of 0.5348 on the test set, 0.0005 lower than the 2nd place.

Tom Liu, Hui Lin, Aggelos K. Katsaggelos et al.

Coronary angiography remains the gold standard for diagnosis of coronary artery disease, the most common cause of death worldwide. While this procedure is performed more than 2 million times annually, there remain few methods for fast and accurate automated measurement of disease and localization of coronary anatomy. Here, we present our solution to the Automatic Region-based Coronary Artery Disease diagnostics using X-ray angiography images (ARCADE) challenge held at MICCAI 2023. For the artery segmentation task, our three-stage approach combines preprocessing and feature selection by classical computer vision to enhance vessel contrast, followed by an ensemble model based on YOLOv8 to propose possible vessel candidates by generating a vessel map. A final segmentation is based on a logic-based approach to reconstruct the coronary tree in a graph-based sorting method. Our entry to the ARCADE challenge placed 3rd overall. Using the official metric for evaluation, we achieved an F1 score of 0.422 and 0.4289 on the validation and hold-out sets respectively.

Hui Lin, Florian Schiffers, Santiago López-Tapia et al.

Unsupervised domain adaptation (UDA) is essential for medical image segmentation, especially in cross-modality data scenarios. UDA aims to transfer knowledge from a labeled source domain to an unlabeled target domain, thereby reducing the dependency on extensive manual annotations. This paper presents DRL-STNet, a novel framework for cross-modality medical image segmentation that leverages generative adversarial networks (GANs), disentangled representation learning (DRL), and self-training (ST). Our method leverages DRL within a GAN to translate images from the source to the target modality. Then, the segmentation model is initially trained with these translated images and corresponding source labels and then fine-tuned iteratively using a combination of synthetic and real images with pseudo-labels and real labels. The proposed framework exhibits superior performance in abdominal organ segmentation on the FLARE challenge dataset, surpassing state-of-the-art methods by 11.4% in the Dice similarity coefficient and by 13.1% in the Normalized Surface Dice metric, achieving scores of 74.21% and 80.69%, respectively. The average running time is 41 seconds, and the area under the GPU memory-time curve is 11,292 MB. These results indicate the potential of DRL-STNet for enhancing cross-modality medical image segmentation tasks.

Hui Lin, Charilaos Apostolidis, Aggelos K. Katsaggelos

Differences in image quality, lighting conditions, and patient demographics pose challenges to automated glaucoma detection from color fundus photography. Brighteye, a method based on Vision Transformer, is proposed for glaucoma detection and glaucomatous feature classification. Brighteye learns long-range relationships among pixels within large fundus images using a self-attention mechanism. Prior to being input into Brighteye, the optic disc is localized using YOLOv8, and the region of interest (ROI) around the disc center is cropped to ensure alignment with clinical practice. Optic disc detection improves the sensitivity at 95% specificity from 79.20% to 85.70% for glaucoma detection and the Hamming distance from 0.2470 to 0.1250 for glaucomatous feature classification. In the developmental stage of the Justified Referral in AI Glaucoma Screening (JustRAIGS) challenge, the overall outcome secured the fifth position out of 226 entries.

Philippe Zhang, Weili Jiang, Yihao Li et al.

Age-related Macular Degeneration (AMD) is a prevalent eye condition affecting visual acuity. Anti-vascular endothelial growth factor (anti-VEGF) treatments have been effective in slowing the progression of neovascular AMD, with better outcomes achieved through timely diagnosis and consistent monitoring. Tracking the progression of neovascular activity in OCT scans of patients with exudative AMD allows for the development of more personalized and effective treatment plans. This was the focus of the Monitoring Age-related Macular Degeneration Progression in Optical Coherence Tomography (MARIO) challenge, in which we participated. In Task 1, which involved classifying the evolution between two pairs of 2D slices from consecutive OCT acquisitions, we employed a fusion CNN network with model ensembling to further enhance the model's performance. For Task 2, which focused on predicting progression over the next three months based on current exam data, we proposed the Patch Progression Masked Autoencoder that generates an OCT for the next exam and then classifies the evolution between the current OCT and the one generated using our solution from Task 1. The results we achieved allowed us to place in the Top 10 for both tasks. Some team members are part of the same organization as the challenge organizers; therefore, we are not eligible to compete for the prize.

Hui Lin, Jiyang Li, Ramy Hussein et al.

Hypertension is a leading risk factor for cardiovascular diseases. Traditional blood pressure monitoring methods are cumbersome and inadequate for continuous tracking, prompting the development of PPG-based cuffless blood pressure monitoring wearables. This study leverages deep learning models, including ResNet and Transformer, to analyze wrist PPG data collected with a smartwatch for efficient hypertension risk screening, eliminating the need for handcrafted PPG features. Using the Home Blood Pressure Monitoring (HBPM) longitudinal dataset of 448 subjects and five-fold cross-validation, our model was trained on over 68k spot-check instances from 358 subjects and tested on real-world continuous recordings of 90 subjects. The compact ResNet model with 0.124M parameters performed significantly better than traditional machine learning methods, demonstrating its effectiveness in distinguishing between healthy and abnormal cases in real-world scenarios.

Bin Wang, Yan Yin, Hui Lin

Recent studies reveal the potential of recurrent neural network transducer (RNN-T) for end-to-end (E2E) speech recognition. Among some most popular E2E systems including RNN-T, Attention Encoder-Decoder (AED), and Connectionist Temporal Classification (CTC), RNN-T has some clear advantages given that it supports streaming recognition and does not have frame-independency assumption. Although significant progresses have been made for RNN-T research, it is still facing performance challenges in terms of training speed and accuracy. We propose attention-based transducer with modification over RNN-T in two aspects. First, we introduce chunk-wise attention in the joint network. Second, self-attention is introduced in the encoder. Our proposed model outperforms RNN-T for both training speed and accuracy. For training, we achieves over 1.7x speedup. With 500 hours LAIX non-native English training data, attention-based transducer yields ~10.6% WER reduction over baseline RNN-T. Trained with full set of over 10K hours data, our final system achieves ~5.5% WER reduction over that trained with the best Kaldi TDNN-f recipe. After 8-bit weight quantization without WER degradation, RTF and latency drop to 0.34~0.36 and 268~409 milliseconds respectively on a single CPU core of a production server.

Yan Yin, Ramon Prieto, Bin Wang et al.

Recent research has shown that attention-based sequence-to-sequence models such as Listen, Attend, and Spell (LAS) yield comparable results to state-of-the-art ASR systems on various tasks. In this paper, we describe the development of such a system and demonstrate its performance on two tasks: first we achieve a new state-of-the-art word error rate of 3.43% on the test clean subset of LibriSpeech English data; second on non-native English speech, including both read speech and spontaneous speech, we obtain very competitive results compared to a conventional system built with the most updated Kaldi recipe.

Zhangyu Xiao, Zhijian Ou, Wei Chu et al.

In this paper, we present an end-to-end automatic speech recognition system, which successfully employs subword units in a hybrid CTC-Attention based system. The subword units are obtained by the byte-pair encoding (BPE) compression algorithm. Compared to using words as modeling units, using characters or subword units does not suffer from the out-of-vocabulary (OOV) problem. Furthermore, using subword units further offers a capability in modeling longer context than using characters. We evaluate different systems over the LibriSpeech 1000h dataset. The subword-based hybrid CTC-Attention system obtains 6.8% word error rate (WER) on the test_clean subset without any dictionary or external language model. This represents a significant improvement (a 12.8% WER relative reduction) over the character-based hybrid CTC-Attention system.

Zhu Kaili, Chuan Wang, Ruobing Li et al.

We treat grammatical error correction (GEC) as a classification problem in this study, where for different types of errors, a target word is identified, and the classifier predicts the correct word form from a set of possible choices. We propose a novel neural network based feature representation and classification model, trained using large text corpora without human annotations. Specifically we use RNNs with attention to represent both the left and right context of a target word. All feature embeddings are learned jointly in an end-to-end fashion. Experimental results show that our novel approach outperforms other classifier methods on the CoNLL-2014 test set (F0.5 45.05%). Our model is simple but effective, and is suitable for industrial production.

Fan Zhang, Fabio Duarte, Ruixian Ma et al.

In this paper, we propose a robust and parsimonious approach using Deep Convolutional Neural Network (DCNN) to recognize and interpret interior space. DCNN has achieved incredible success in object and scene recognition. In this study we design and train a DCNN to classify a pre-zoning indoor space, and from a single phone photo to recognize the learned space features, with no need of additional assistive technology. We collect more than 600,000 images inside MIT campus buildings to train our DCNN model, and achieved 97.9% accuracy in validation dataset and 81.7% accuracy in test dataset based on spatial-scale fixed model. Furthermore, the recognition accuracy and spatial resolution can be potentially improved through multiscale classification model. We identify the discriminative image regions through Class Activating Mapping (CAM) technique, to observe the model's behavior in how to recognize space and interpret it in an abstract way. By evaluating the results with misclassification matrix, we investigate the visual spatial feature of interior space by looking into its visual similarity and visual distinctiveness, giving insights into interior design and human indoor perception and wayfinding research. The contribution of this paper is threefold. First, we propose a robust and parsimonious approach for indoor navigation using DCNN. Second, we demonstrate that DCNN also has a potential capability in space feature learning and recognition, even under severe appearance changes. Third, we introduce a DCNN based approach to look into the visual similarity and visual distinctiveness of interior space.

Hui Lin, Jeff A. Bilmes

We introduce a method to learn a mixture of submodular "shells" in a large-margin setting. A submodular shell is an abstract submodular function that can be instantiated with a ground set and a set of parameters to produce a submodular function. A mixture of such shells can then also be so instantiated to produce a more complex submodular function. What our algorithm learns are the mixture weights over such shells. We provide a risk bound guarantee when learning in a large-margin structured-prediction setting using a projected subgradient method when only approximate submodular optimization is possible (such as with submodular function maximization). We apply this method to the problem of multi-document summarization and produce the best results reported so far on the widely used NIST DUC-05 through DUC-07 document summarization corpora.