Prediction Performance of Radiomic Features When Obtained using an Object Detection Framework

Chegraoui, Hamza; Rebei, Amine; Philippe, Cathy; Frouin, Vincent

doi:10.1109/isbi48211.2021.9434148

Cited by 1 publication

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We were able to obtain satisfying segmentation for the DIPG. These segmentations and performance will allow us to perform further clinical work to characterise this rare pathology using radiomics [ 47 ].…”

Section: Discussionmentioning

confidence: 99%

Object Detection Improves Tumour Segmentation in MR Images of Rare Brain Tumours

Chegraoui

Philippe

Dangouloff‐Ros

et al. 2021

Cancers

Self Cite

View full text Add to dashboard Cite

Tumour lesion segmentation is a key step to study and characterise cancer from MR neuroradiological images. Presently, numerous deep learning segmentation architectures have been shown to perform well on the specific tumour type they are trained on (e.g., glioblastoma in brain hemispheres). However, a high performing network heavily trained on a given tumour type may perform poorly on a rare tumour type for which no labelled cases allows training or transfer learning. Yet, because some visual similarities exist nevertheless between common and rare tumours, in the lesion and around it, one may split the problem into two steps: object detection and segmentation. For each step, trained networks on common lesions could be used on rare ones following a domain adaptation scheme without extra fine-tuning. This work proposes a resilient tumour lesion delineation strategy, based on the combination of established elementary networks that achieve detection and segmentation. Our strategy allowed us to achieve robust segmentation inference on a rare tumour located in an unseen tumour context region during training. As an example of a rare tumour, Diffuse Intrinsic Pontine Glioma (DIPG), we achieve an average dice score of 0.62 without further training or network architecture adaptation.

show abstract

Section: Discussionmentioning

confidence: 99%