OBJECTIVE: In a few patients with mild COVID-19, there is a possibility of the infection becoming severe or critical in the future. This work aims to identify high-risk patients who have a high probability of changing from mild to critical COVID-19 (only account for 5% of cases). METHODS: Using traditional convolutional neural networks for classification may not be suitable to identify this 5% of high risk patients from an entire dataset due to the highly imbalanced label distribution. To address this problem, we propose a Mix Contrast model, which matches original features with mixed features for contrastive learning. Three modules are proposed for training the model: 1) a cumulative learning strategy for synthesizing the mixed feature; 2) a commutative feature combination module for learning the commutative law of feature concatenation; 3) a united pairwise loss assigning adaptive weights for sample pairs with different class anchors based on their current optimization status. RESULTS: We collect a multi-center computed tomography dataset including 918 confirmed COVID-19 patients from four hospitals and evaluate the proposed method on both the COVID-19 mild-to-critical prediction and COVID-19 diagnosis tasks. For mild-to-critical prediction, the experimental results show a recall of 0.80 and a specificity of 0.815. For diagnosis, the model shows comparable results with deep neural networks using a large dataset. Our method demonstrates improvements when the amount of training data is small or imbalanced. SIGNIFICANCE: Identifying mild-to-critical COVID-19 patients is important for early prevention and personalized treatment planning.
OBJECTIVE: In a few patients with mild COVID-19, there is a possibility of the infection becoming severe or critical in the future. This work aims to identify high-risk patients who have a high probability of changing from mild to critical COVID-19 (only account for 5% of cases). METHODS: Using traditional convolutional neural networks for classification may not be suitable to identify this 5% of high risk patients from an entire dataset due to the highly imbalanced label distribution. To address this problem, we propose a Mix Contrast model, which matches original features with mixed features for contrastive learning. Three modules are proposed for training the model: 1) a cumulative learning strategy for synthesizing the mixed feature; 2) a commutative feature combination module for learning the commutative law of feature concatenation; 3) a united pairwise loss assigning adaptive weights for sample pairs with different class anchors based on their current optimization status. RESULTS: We collect a multi-center computed tomography dataset including 918 confirmed COVID-19 patients from four hospitals and evaluate the proposed method on both the COVID-19 mild-to-critical prediction and COVID-19 diagnosis tasks. For mild-to-critical prediction, the experimental results show a recall of 0.80 and a specificity of 0.815. For diagnosis, the model shows comparable results with deep neural networks using a large dataset. Our method demonstrates improvements when the amount of training data is small or imbalanced. SIGNIFICANCE: Identifying mild-to-critical COVID-19 patients is important for early prevention and personalized treatment planning.
Authors: Rina D Rudyanto; Sjoerd Kerkstra; Eva M van Rikxoort; Catalin Fetita; Pierre-Yves Brillet; Christophe Lefevre; Wenzhe Xue; Xiangjun Zhu; Jianming Liang; Ilkay Öksüz; Devrim Ünay; Kamuran Kadipaşaoğlu; Raúl San José Estépar; James C Ross; George R Washko; Juan-Carlos Prieto; Marcela Hernández Hoyos; Maciej Orkisz; Hans Meine; Markus Hüllebrand; Christina Stöcker; Fernando Lopez Mir; Valery Naranjo; Eliseo Villanueva; Marius Staring; Changyan Xiao; Berend C Stoel; Anna Fabijanska; Erik Smistad; Anne C Elster; Frank Lindseth; Amir Hossein Foruzan; Ryan Kiros; Karteek Popuri; Dana Cobzas; Daniel Jimenez-Carretero; Andres Santos; Maria J Ledesma-Carbayo; Michael Helmberger; Martin Urschler; Michael Pienn; Dennis G H Bosboom; Arantza Campo; Mathias Prokop; Pim A de Jong; Carlos Ortiz-de-Solorzano; Arrate Muñoz-Barrutia; Bram van Ginneken Journal: Med Image Anal Date: 2014-07-23 Impact factor: 8.545
Authors: Samuel G Armato; Geoffrey McLennan; Luc Bidaut; Michael F McNitt-Gray; Charles R Meyer; Anthony P Reeves; Binsheng Zhao; Denise R Aberle; Claudia I Henschke; Eric A Hoffman; Ella A Kazerooni; Heber MacMahon; Edwin J R Van Beeke; David Yankelevitz; Alberto M Biancardi; Peyton H Bland; Matthew S Brown; Roger M Engelmann; Gary E Laderach; Daniel Max; Richard C Pais; David P Y Qing; Rachael Y Roberts; Amanda R Smith; Adam Starkey; Poonam Batrah; Philip Caligiuri; Ali Farooqi; Gregory W Gladish; C Matilda Jude; Reginald F Munden; Iva Petkovska; Leslie E Quint; Lawrence H Schwartz; Baskaran Sundaram; Lori E Dodd; Charles Fenimore; David Gur; Nicholas Petrick; John Freymann; Justin Kirby; Brian Hughes; Alessi Vande Casteele; Sangeeta Gupte; Maha Sallamm; Michael D Heath; Michael H Kuhn; Ekta Dharaiya; Richard Burns; David S Fryd; Marcos Salganicoff; Vikram Anand; Uri Shreter; Stephen Vastagh; Barbara Y Croft Journal: Med Phys Date: 2011-02 Impact factor: 4.071