Deep learning with PyTorch Medical Imaging Competitions

This course is outdated because it is based on pytorch lightning and alot of thing has been changed since the release of this course.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.