|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/deep-learning-in-action-medical-imaging-competitions/
课程评论：没有评论
**课程名称：** Deep learning with PyTorch Medical Imaging Competitions **课程概述：** 本课程旨在教授学员如何利用PyTorch参与医学影像竞赛。课程内容侧重于实践操作，涵盖了从数据获取、预处理、模型训练到结果提交的全过程。尽管课程使用的PyTorch Lightning版本和部分数据集已过时，且不适合医学影像领域的初学者，但其关于医学影像竞赛参与策略和核心概念的讲解仍然具有参考价值。 **课程亮点：** * **实战导向：** 重点在于如何参加竞赛、处理数据、训练模型并提交结果。 * **广泛的主题：** 涵盖了多种医学影像竞赛类型，包括二分类、多分类（如CXR-covid19）、多标签分类（如ODIR）以及语义分割。 * **高级技术：** 涉及数据增强（Albumentations）、自定义数据加载器、预训练模型的使用、学习率调度、交叉验证、模型集成、自定义损失函数（Focal Loss）和评估指标。 * **特定数据集处理：** 讲解了如何处理NIfTI等格式的医学影像数据，以及如何对图像和掩码进行同步增强。 * **案例分析：** 包含了一个关于COVID-19感染百分比估计的Capstone项目，并深入剖析了解决方案和模型集成技巧。 **目标学员：** 已具备CNN、优化器、ResNet、DenseNet等基础知识，并有MNIST或CIFAR等数据集训练经验，希望将技能应用于真实医学影像竞赛的学员。 **重要提示：** * 该课程已过时，但其核心概念仍具参考价值。 * 课程不提供基础概念讲解，不适合初学者。 * 部分数据集已不再公开可用。 * 作者不对此课程提供支持，但因内容长度限制，无法将其设为免费。
This course is outdated because it is based on pytorch lightning and alot of thing has been changed since the release of this course. Further some of datasets in this course are no more available for public anymore. So I am not providing support for this course. I want to make this course free, but udemy is not allowing to do so because of content length. The reason why I am not archiving this course, because its still relevant if you want to gain concept of medical imaging competition. Greetings. This course is not intended for beginners, and it is more practically oriented. Though I tried my best to explain why I performed a particular step, I put little to no effort into explaining basic concepts such as Convolution neural networks, how the optimizer works, how ResNet, DenseNet model was created etc. This course is for those who have worked on CIFAR, MNIST data and want to work in real-life scenariosMy focus was mainly on how to participate in a competition, get data and train a model on that data, and make a submission. In this course PyTorch lightning is usedThe course covers the following topicsBinary ClassificationGet the dataRead dataApply augmentationHow data flows from folders to GPUTrain a modelGet accuracy metric and lossMulti-class classification (CXR-covid19 competition)Albumentations augmentationsWrite a custom data loaderUse publicly pre-trained model on XRayUse learning rate schedulerUse different callback functionsDo five fold cross-validations when images are in a folderTrain, save and load modelGet test predictions via ensemble learningSubmit predictions to the competition pageMulti-label classification (ODIR competition)Apply augmentation on two images simultaneouslyMake a parallel network to take two images simultaneouslyModify binary cross-entropy loss to focal lossUse custom metric provided by competition organizer to get the evaluationGet predictions of test setCapstone Project (Covid-19 Infection Percentage Estimation)How to come up with a solutionCode walk-throughThe secret sauce of model ensembleSemantic SegmentationData download and read data from nii.gzApply augmentation to image and mask simultaneouslyTrain model on NIfTI imagesPlot test images and corresponding ground truth and predicted masks
