Region Focus Network for Joint Optic Disc and Cup Segmentation

Li, Ge; Li, Changsheng; Zeng, Chan; Gao, Peng

doi:10.1609/aaai.v34i01.5418

Cited by 11 publications

(6 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of polar image transforms in neural networks was explored previously, including in the field of medical image segmentation [5]. Esteves et al [6] train an end-to-end network which predicts a polar origin, transforms the image to polar coordinates and then performs classification.…”

Section: A Related Workmentioning

confidence: 99%

Using the Polar Transform for Efficient Deep Learning-Based Aorta Segmentation in CTA Images

Benčević¹,

Habijan²,

Galić³

et al. 2022

Preprint

View full text Add to dashboard Cite

Medical image segmentation often requires segmenting multiple elliptical objects on a single image. This includes, among other tasks, segmenting vessels such as the aorta in axial CTA slices. In this paper, we present a general approach to improving the semantic segmentation performance of neural networks in these tasks and validate our approach on the task of aorta segmentation. We use a cascade of two neural networks, where one performs a rough segmentation based on the U-Net architecture and the other performs the final segmentation on polar image transformations of the input. Connected component analysis of the rough segmentation is used to construct the polar transformations, and predictions on multiple transformations of the same image are fused using hysteresis thresholding. We show that this method improves aorta segmentation performance without requiring complex neural network architectures. In addition, we show that our approach improves robustness and pixel-level recall while achieving segmentation performance in line with the state of the art.

show abstract

Section: A Related Workmentioning

confidence: 99%

Using the Polar Transform for Efficient Deep Learning-Based Aorta Segmentation in CTA Images

Benčević¹,

Habijan²,

Galić³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Several image segmentation methods were proposed that utilize polar coordinates. Liu et al [5] proposed an approach they call Cartesian-polar dual-domain network (DDNet) to perform optic disc and cup segmentation in retinal fundus images. The neural network contains two encoding branches, one for a Cartesian input image and another for the polar transformation of the same input image.…”

Section: A Related Work 1) Combining Polar Coordinates and Neural Networkmentioning

confidence: 99%

“…We trained all models up to a maximum of 200 epochs and used checkpoints after each epoch to store the model with the best validation loss. We modify the Dice coefficient to act as a loss function as shown in (5).…”

Section: B Implementation Detailsmentioning

confidence: 99%

Training on Polar Image Transformations Improves Biomedical Image Segmentation

et al. 2021

View full text Add to dashboard Cite

A key step in medical image-based diagnosis is image segmentation. A common use case for medical image segmentation is the identification of single structures of an elliptical shape. Most organs like the heart and kidneys fall into this category, as well as skin lesions, polyps, and other types of abnormalities. Neural networks have dramatically improved medical image segmentation results, but still require large amounts of training data and long training times to converge. In this paper, we propose a general way to improve neural network segmentation performance and data efficiency on medical imaging segmentation tasks where the goal is to segment a single roughly elliptically distributed object. We propose training a neural network on polar transformations of the original dataset, such that the polar origin for the transformation is the center point of the object. This results in a reduction of dimensionality as well as a separation of segmentation and localization tasks, allowing the network to more easily converge. Additionally, we propose two different approaches to obtaining an optimal polar origin: (1) estimation via a segmentation trained on non-polar images and (2) estimation via a model trained to predict the optimal origin. We evaluate our method on the tasks of liver, polyp, skin lesion, and epicardial adipose tissue segmentation. We show that our method produces state-of-the-art results for lesion, liver, and polyp segmentation and performs better than most common neural network architectures for biomedical image segmentation. Additionally, when used as a pre-processing step, our method generally improves data efficiency across datasets and neural network architectures.

show abstract

“…To reduce the impact of such annotator-related biases, each training sample can be annotated by multiple medical professionals independently [6,23,26,31] (see Figure 1), and a proxy ground truth is generated via majority voting [9], label fusion [3,22,24,35,43,44], or label sampling [13]. It is worth noting that, in many cases, the variable annotations provided by multiple annotators are all reasonable.…”

Section: Encoder Decoder Stochastic Error Modelingmentioning

confidence: 99%

Modeling Annotator Preference and Stochastic Annotation Error for Medical Image Segmentation

Liao¹,

Hu²,

Xia³

2021

Preprint

View full text Add to dashboard Cite

Manual annotation of medical images is highly subjective, leading to inevitable and huge annotation biases. Deep learning models may surpass human performance on a variety of tasks, but they may also mimic or amplify these biases. Although we can have multiple annotators and fuse their annotations to reduce stochastic errors, we cannot use this strategy to handle the bias caused by annotators' preferences. In this paper, we highlight the issue of annotator-related biases on medical image segmentation tasks, and propose a Preference-involved Annotation Distribution Learning (PADL) framework to address it from the perspective of disentangling an annotator's preference from stochastic errors using distribution learning so as to produce not only a meta segmentation but also the segmentation possibly made by each annotator. Under this framework, a stochastic error modeling (SEM) module estimates the meta segmentation map and average stochastic error map, and a series of human preference modeling (HPM) modules estimate each annotator's segmentation and the corresponding stochastic error. We evaluated our PADL framework on two medical image benchmarks with different imaging modalities, which have been annotated by multiple medical professionals, and achieved promising performance on all five medical image segmentation tasks.

show abstract

Region Focus Network for Joint Optic Disc and Cup Segmentation

Cited by 11 publications

References 19 publications

Using the Polar Transform for Efficient Deep Learning-Based Aorta Segmentation in CTA Images

Using the Polar Transform for Efficient Deep Learning-Based Aorta Segmentation in CTA Images

Training on Polar Image Transformations Improves Biomedical Image Segmentation

Modeling Annotator Preference and Stochastic Annotation Error for Medical Image Segmentation

Contact Info

Product

Resources

About