Single-Shot Lightweight Model For The Detection of Lesions And The Prediction of

Single-Shot Lightweight Model For The Detection of Lesions And The Prediction of COVID-19 From Chest CT Scans

We introduce a lightweight model based on Mask R-CNN with ResNet18 and ResNet34 backbone models thatsegments lesions and predicts COVID-19 from chest CT scans in a single shot. The model requires a small dataset totrain: 650 images for the segmentation branch and 3000 for the classification branch, and it is evaluated on 21292 imagesto achieve a 42.45% average precision (main MS COCO criterion) on the segmentation test split (100 images), 93.00%COVID-19 sensitivity and F1-score of 96.76% on the classification test split (21192 images) across 3 classes: COVID-19,Common Pneumonia and Control/Negative.The full source code, models and pretrained weights are available onhttps://github.com/AlexTS1980/COVID-Single-Shot-Model.

胸部CT扫描的单发轻量模型，用于病变的检测和COVID-19的预测

我们基于ResNet18和ResNet34主干模型引入基于Mask R-CNN的轻量级模型，该模型可以分割病变并通过一次胸部CT扫描预测COVID-19。该模型需要训练一个小的数据集：分割分支为650张图像，分类分支为3000张图像，并且对21292张图像进行了评估，以在分割测试分割（100张图像）上达到42.45％的平均精度（主要MS COCO标准） ），93.00％的COVID-19敏感性和96.76％的F1分数在21个类别的分类测试中分为21个类别：COVID-19，普通肺炎和对照/阴性。.. 完整的源代码，模型和预训练的权重可在https://github.com/AlexTS1980/COVID-Single-Shot-Model上获得。 （阅读更多）