More Like this

1. Generative AI enables medical image segmentation in ultra low-data regimes

   https://doi.org/10.1038/s41467-025-61754-6  

   Zhang, Li; Jindal, Basu; Alaa, Ahmed; Weinreb, Robert; Wilson, David; Segal, Eran; Zou, James; Xie, Pengtao (July 2025, Nature Communications)

   Semantic segmentation of medical images is pivotal in applications like disease diagnosis and treatment planning. While deep learning automates this task effectively, it struggles in ultra low-data regimes for the scarcity of annotated segmentation masks. To address this, we propose a generative deep learning framework that produces high-quality image-mask pairs as auxiliary training data. Unlike traditional generative models that separate data generation from model training, ours uses multi-level optimization for end-to-end data generation. This allows segmentation performance to guide the generation process, producing data tailored to improve segmentation outcomes. Our method demonstrates strong generalization across 11 medical image segmentation tasks and 19 datasets, covering various diseases, organs, and modalities. It improves performance by 10–20% (absolute) in both same- and out-of-domain settings and requires 8–20 times less training data than existing approaches. This greatly enhances the feasibility and cost-effectiveness of deep learning in data-limited medical imaging scenarios. 

   more » « less
2. ComputeCOVID19+: Accelerating COVID-19 Diagnosis and Monitoring via High-Performance Deep Learning on CT Images

   https://doi.org/10.1145/3472456.3473523  

   Goel, Garvit; Gondhalekar, Atharva; Qi, Jingyuan; Zhang, Zhicheng; Cao, Guohua; Feng, Wu-chun (August 2021, 50th International Conference on Parallel Processing)

   null (Ed.)

   The COVID-19 pandemic has highlighted the importance of diagnosis and monitoring as early and accurately as possible. However, the reverse-transcription polymerase chain reaction (RT-PCR) test results in two issues: (1) protracted turnaround time from sample collection to testing result and (2) compromised test accuracy, as low as 67%, due to when the test is administered and due to how the samples are collected, handled, and delivered to the lab to conduct the RT-PCR test. Thus, we present ComputeCOVID19+, our computed tomography-based framework to improve the testing speed and accuracy of COVID-19 (plus its variants) via a deep learning-based network for CT image enhancement called DDnet. To demonstrate its speed and accuracy, we evaluate ComputeCOVID19+ across many sources of computed tomography (CT) images and on many heterogeneous platforms, including multi-core CPU, many-core GPU, and even FPGA. Our results show that ComputeCOVID19+ can significantly shorten the turnaround time from days to minutes and improve the testing accuracy to 91%. 

   more » « less
3. Machine-Learning-Enabled Diagnostics with Improved Visualization of Disease Lesions in Chest X-ray Images

   https://doi.org/10.3390/diagnostics14161699  

   Rahman, Md Fashiar; Tseng, Tzu-Liang Bill; Pokojovy, Michael; McCaffrey, Peter; Walser, Eric; Moen, Scott; Vo, Alex; Ho, Johnny C (August 2024, Diagnostics)

   The class activation map (CAM) represents the neural-network-derived region of interest, which can help clarify the mechanism of the convolutional neural network’s determination of any class of interest. In medical imaging, it can help medical practitioners diagnose diseases like COVID-19 or pneumonia by highlighting the suspicious regions in Computational Tomography (CT) or chest X-ray (CXR) film. Many contemporary deep learning techniques only focus on COVID-19 classification tasks using CXRs, while few attempt to make it explainable with a saliency map. To fill this research gap, we first propose a VGG-16-architecture-based deep learning approach in combination with image enhancement, segmentation-based region of interest (ROI) cropping, and data augmentation steps to enhance classification accuracy. Later, a multi-layer Gradient CAM (ML-Grad-CAM) algorithm is integrated to generate a class-specific saliency map for improved visualization in CXR images. We also define and calculate a Severity Assessment Index (SAI) from the saliency map to quantitatively measure infection severity. The trained model achieved an accuracy score of 96.44% for the three-class CXR classification task, i.e., COVID-19, pneumonia, and normal (healthy patients), outperforming many existing techniques in the literature. The saliency maps generated from the proposed ML-GRAD-CAM algorithm are compared with the original Gran-CAM algorithm. 

   more » « less
4. Calibrated bagging deep learning for image semantic segmentation: A case study on COVID-19 chest X-ray image

   https://doi.org/10.1371/journal.pone.0276250  

   Nwosu, Lucy; Li, Xiangfang; Qian, Lijun; Kim, Seungchan; Dong, Xishuang (November 2022, PLOS ONE)

   Hemanth, Jude (Ed.)

   Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) causes coronavirus disease 2019 (COVID-19). Imaging tests such as chest X-ray (CXR) and computed tomography (CT) can provide useful information to clinical staff for facilitating a diagnosis of COVID-19 in a more efficient and comprehensive manner. As a breakthrough of artificial intelligence (AI), deep learning has been applied to perform COVID-19 infection region segmentation and disease classification by analyzing CXR and CT data. However, prediction uncertainty of deep learning models for these tasks, which is very important to safety-critical applications like medical image processing, has not been comprehensively investigated. In this work, we propose a novel ensemble deep learning model through integrating bagging deep learning and model calibration to not only enhance segmentation performance, but also reduce prediction uncertainty. The proposed method has been validated on a large dataset that is associated with CXR image segmentation. Experimental results demonstrate that the proposed method can improve the segmentation performance, as well as decrease prediction uncertainty. 

   more » « less
5. The Existence of at Least Three Genomic Signature Patterns and at Least Seven Subtypes of COVID-19 and the End of the Disease

   https://doi.org/10.3390/vaccines10050761  

   Zhang, Zhengjun (May 2022, Vaccines)

   Hoping to find genomic clues linked to COVID-19 and end the pandemic has driven scientists’ tremendous efforts to try all kinds of research. Signs of progress have been achieved but are still limited. This paper intends to prove the existence of at least three genomic signature patterns and at least seven subtypes of COVID-19 driven by five critical genes (the smallest subset of genes) using three blood-sampled datasets. These signatures and subtypes provide crucial genomic information in COVID-19 diagnosis (including ICU patients), research focuses, and treatment methods. Unlike existing approaches focused on gene fold-changes and pathways, gene-gene nonlinear and competing interactions are the driving forces in finding the signature patterns and subtypes. Furthermore, the method leads to high accuracy with hospitalized patients, showing biological and mathematical equivalences between COVID-19 status and the signature patterns and a methodological advantage over other methods that cannot lead to high accuracy. As a result, as new biomarkers, the new findings and genomic clues can be much more informative than other findings for interpreting biological mechanisms, developing the second (third) generation of vaccines, antiviral drugs, and treatment methods, and eventually bringing new hopes of an end to the pandemic. 

   more » « less