An amplified-target loss approach for photoreceptor layer segmentation in pathological OCT scans
This work addresses the challenge of accurate photoreceptor segmentation in pathological OCT scans for medical imaging applications, representing an incremental improvement over existing methods.
The paper tackled the problem of segmenting the photoreceptor layer in pathological retinal OCT scans, where standard loss functions lead to poor generalization on unseen lesions, and introduced an amplified-target loss that penalizes errors in central image areas, resulting in increased performance compared to standard losses.
Segmenting anatomical structures such as the photoreceptor layer in retinal optical coherence tomography (OCT) scans is challenging in pathological scenarios. Supervised deep learning models trained with standard loss functions are usually able to characterize only the most common disease appeareance from a training set, resulting in suboptimal performance and poor generalization when dealing with unseen lesions. In this paper we propose to overcome this limitation by means of an augmented target loss function framework. We introduce a novel amplified-target loss that explicitly penalizes errors within the central area of the input images, based on the observation that most of the challenging disease appeareance is usually located in this area. We experimentally validated our approach using a data set with OCT scans of patients with macular diseases. We observe increased performance compared to the models that use only the standard losses. Our proposed loss function strongly supports the segmentation model to better distinguish photoreceptors in highly pathological scenarios.