Extending Pretrained Segmentation Networks with Additional Anatomical Structures

by   Firat Ozdemir, et al.

Comprehensive surgical planning require complex patient-specific anatomical models. For instance, functional muskuloskeletal simulations necessitate all relevant structures to be segmented, which could be performed in real-time using deep neural networks given sufficient annotated samples. Such large datasets of multiple structure annotations are costly to procure and are often unavailable in practice. Nevertheless, annotations from different studies and centers can be readily available, or become available in the future in an incremental fashion. We propose a class-incremental segmentation framework for extending a deep network trained for some anatomical structure to yet another structure using a small incremental annotation set. Through distilling knowledge from the current state of the framework, we bypass the need for a full retraining. This is a meta-method to extend any choice of desired deep segmentation network with only a minor addition per structure, which makes it suitable for lifelong class-incremental learning and applicable also for future deep neural network architectures. We evaluated our methods on a public knee dataset of 100 MR volumes. Through varying amount of incremental annotation ratios, we show how our proposed method can retain the previous anatomical structure segmentation performance superior to the conventional finetuning approach. In addition, our framework inherently exploits transferable knowledge from previously trained structures to incremental tasks, demonstrated by superior results compared to non-incremental training. With the presented method, new anatomical structures can be learned without catastrophic forgetting of older structures and without extensive increase of memory and complexity.


Incremental Learning for Heterogeneous Structure Segmentation in Brain Tumor MRI

Deep learning (DL) models for segmenting various anatomical structures h...

Continual Class Incremental Learning for CT Thoracic Segmentation

Deep learning organ segmentation approaches require large amounts of ann...

Knowledge Consolidation based Class Incremental Online Learning with Limited Data

We propose a novel approach for class incremental online learning in a l...

Learn the new, keep the old: Extending pretrained models with new anatomy and images

Deep learning has been widely accepted as a promising solution for medic...

A Contrastive Distillation Approach for Incremental Semantic Segmentation in Aerial Images

Incremental learning represents a crucial task in aerial image processin...

PHiSeg: Capturing Uncertainty in Medical Image Segmentation

Segmentation of anatomical structures and pathologies is inherently ambi...

Incremental Evolution and Development of Deep Artificial Neural Networks

NeuroEvolution (NE) methods are known for applying Evolutionary Computat...

Please sign up or login with your details

Forgot password? Click here to reset