MIScnn: A Framework for Medical Image Segmentation with Convolutional Neural Networks and Deep Learning

Dominik Müller,Frank Kramer

doi:10.24926/548719.074

Abstract

The increased availability and usage of modern medical imaging induced a strong need for automatic medical image segmentation. Still, current image segmentation platforms do not provide the required functionalities for plain setup of medical image segmentation pipelines. Already implemented pipelines are commonly standalone software, optimized on a specific public data set. Therefore, this paper introduces the open-source Python library MIScnn. The aim of MIScnn is to provide an intuitive API allowing fast building of medical image segmentation pipelines including data I/O, preprocessing, data augmentation, patch-wise analysis, metrics, a library with state-of-the-art deep learning models and model utilization like training, prediction, as well as fully automatic evaluation (e.g. cross-validation). Similarly, high configurability and multiple open interfaces allow full pipeline customization. Running a cross-validation with MIScnn on the Kidney Tumor Segmentation Challenge 2019 data set (multi-class semantic segmentation with 300 CT scans) resulted into a powerful predictor based on the standard 3D U-Net model. With this experiment, we could show that the MIScnn framework enables researchers to rapidly set up a complete medical image segmentation pipeline by using just a few lines of code. The source code for MIScnn is available in the Git repository: https://github.com/frankkramer-lab/MIScnn .

Highlights

Medical imaging became a standard in diagnosis and medical intervention for the visual representation of the functionality of organs and tissues
For all CT scans, a ground truth semantic segmentation was created by experts
The 3-fold cross-validation of 120 CT scans for kidney and tumor segmentation were evaluated through several metrics: Tversky loss, Dice coefficient, class-wise Dice coefficient, categorical cross-entropy, categorical accuracy, and two Dice score metrics provided by the Kidney Tumor Segmentation Challenge 2019 (KiTS19) challenge

Summary

Introduction

Medical imaging became a standard in diagnosis and medical intervention for the visual representation of the functionality of organs and tissues. Medical image segmentation models with a convolutional neural network architecture has become quite powerful and achieved similar results performance-wise as radiologists [5,12]. These models have been standalone applications with optimized architectures, preprocessing procedures, data augmentations and metrics specific for their data set and corresponding segmentation problem [9]. Developed medical image segmentation platforms, like NiftyNet [13], are powerful tools and an excellent first step for standardized medical image segmentation pipelines They are designed more like configurable software instead of frameworks. They lack modular pipeline blocks to offer researchers the opportunity for easy customization and to help developing their own software for their specific segmentation problems

Methods

Results

Discussion

Conclusion