Benchmarking Deep Learning Models and Automated Model Design for COVID-19 Detection with Chest CT Scans

COVID-19 pandemic has spread all over the world for months. As its transmissibility and high pathogenicity seriously threaten peoples lives, the accurate and fast detection of the COVID-19 infection is crucial. Although many recent studies have shown that deep learning based solutions can help detect COVID-19 based on chest CT scans, there lacks a consistent and systematic comparison and evaluation on these techniques. In this paper, we first build a clean and segmented CT dataset called Clean-CC-CCII by fixing the errors and removing some noises in a large CT scan dataset CC-CCII with three classes: novel coronavirus pneumonia (NCP), common pneumonia (CP), and normal controls (Normal). After cleaning, our dataset consists of a total of 340,190 slices of 3,993 scans from 2,698 patients. Then we benchmark and compare the performance of a series of state-of-the-art (SOTA) 3D and 2D convolutional neural networks (CNNs). The results show that 3D CNNs outperform 2D CNNs in general. With extensive effort of hyperparameter tuning, we find that the 3D CNN model DenseNet3D121 achieves the highest accuracy of 88.63% (F1-score is 88.14% and AUC is 0.940), and another 3D CNN model ResNet3D34 achieves the best AUC of 0.959 (accuracy is 87.83% and F1-score is 86.04%). We further demonstrate that the mixup data augmentation technique can largely improve the model performance. At last, we design an automated deep learning methodology to generate a lightweight deep learning model MNas3DNet41 that achieves an accuracy of 87.14%, F1-score of 87.25%, and AUC of 0.957, which are on par with the best models made by AI experts. The automated deep learning design is a promising methodology that can help health-care professionals develop effective deep learning models using their private data sets. Our Clean-CC-CCII dataset and source code are available at: https://github.com/HKBU-HPML/HKBU_HPML_COVID-19.

Robust Quantization for General Similarity Search.

The recent years have witnessed the emerging of vector quantization (VQ) techniques for efficient similarity search. VQ partitions the feature space into a set of codewords and encodes data points as integer indices using the codewords. Then the distance between data points can be efficiently approximated by simple memory lookup operations. By the compact quantization, the storage cost, and searching complexity are significantly reduced, thereby facilitating efficient large-scale similarity search. However, the performance of several celebrated VQ approaches degrades significantly when dealing with noisy data. In addition, it can barely facilitate a wide range of applications as the distortion measurement only limits to ℓ2 norm. To address the shortcomings of the squared Euclidean (ℓ2,2 norm) loss function employed by the VQ approaches, in this paper, we propose a novel robust and general VQ framework, named RGVQ, to enhance both robustness and generalization of VQ approaches. Specifically, a ℓp,q-norm loss function is proposed to conduct the ℓp-norm similarity search, rather than the ℓ2 norm search, and the q-th order loss is used to enhance the robustness. Despite the fact that changing the loss function to ℓp,q norm makes VQ approaches more robust and generic, it brings us a challenge that a non-smooth and non-convex orthogonality constrained ℓp,q-norm function has to be minimized. To solve this problem, we propose a novel and efficient optimization scheme and specify it to VQ approaches and theoretically prove its convergence. Extensive experiments on benchmark data sets demonstrate that the proposed RGVQ is better than the original VQ for several approaches, especially when searching similarity in noisy data.

Large-Scale Cross-Modality Search via Collective Matrix Factorization Hashing.

By transforming data into binary representation, i.e., Hashing, we can perform high-speed search with low storage cost, and thus, Hashing has collected increasing research interest in the recent years. Recently, how to generate Hashcode for multimodal data (e.g., images with textual tags, documents with photos, and so on) for large-scale cross-modality search (e.g., searching semantically related images in database for a document query) is an important research issue because of the fast growth of multimodal data in the Web. To address this issue, a novel framework for multimodal Hashing is proposed, termed as Collective Matrix Factorization Hashing (CMFH). The key idea of CMFH is to learn unified Hashcodes for different modalities of one multimodal instance in the shared latent semantic space in which different modalities can be effectively connected. Therefore, accurate cross-modality search is supported. Based on the general framework, we extend it in the unsupervised scenario where it tries to preserve the Euclidean structure, and in the supervised scenario where it fully exploits the label information of data. The corresponding theoretical analysis and the optimization algorithms are given. We conducted comprehensive experiments on three benchmark data sets for cross-modality search. The experimental results demonstrate that CMFH can significantly outperform several state-of-the-art cross-modality Hashing methods, which validates the effectiveness of the proposed CMFH.