Training a single multi-class convolutional segmentation network using multiple datasets with heterogeneous labels: preliminary results

Kong, Fanjie; Chen, Cheng; Huang, Bo-Wun; Collins, Leslie M.; Bradbury, Kyle; Malof, Jordan M.

doi:10.1109/igarss.2019.8898617

Cited by 6 publications

(6 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Only a few works have been done to solve the problem. Some works [35], [36] design hierarchical classifier for multiple heterogeneous datasets. Each classifier classifies the children labels of a node and the whole classifier is trained.…”

Section: B Segmentation Over Multiple Datasetsmentioning

confidence: 99%

Multi-Organ Segmentation Over Partially Labeled Datasets With Multi-Scale Feature Abstraction

Fang

Yan

2020

IEEE Trans. Med. Imaging

165

View full text Add to dashboard Cite

Shortage of fully annotated datasets has been a limiting factor in developing deep learning based image segmentation algorithms and the problem becomes more pronounced in multi-organ segmentation. In this paper, we propose a unified training strategy that enables a novel multi-scale deep neural network to be trained on multiple partially labeled datasets for multi-organ segmentation. In addition, a new network architecture for multi-scale feature abstraction is proposed to integrate pyramid input and feature analysis into a U-shape pyramid structure. To bridge the semantic gap caused by directly merging features from different scales, an equal convolutional depth mechanism is introduced. Furthermore, we employ a deep supervision mechanism to refine the outputs in different scales. To fully leverage the segmentation features from all the scales, we design an adaptive weighting layer to fuse the outputs in an automatic fashion. All these mechanisms together are integrated into a Pyramid Input Pyramid Output Feature Abstraction Network (PIPO-FAN). Our proposed method was evaluated on four publicly available datasets, including BTCV, LiTS, KiTS and Spleen, where very promising performance has been achieved. The source code of this work is publicly shared at https://github.com/DIAL-RPI/PIPO-FAN to facilitate others to reproduce the work and build their own models using the introduced mechanisms.

show abstract

Section: B Segmentation Over Multiple Datasetsmentioning

confidence: 99%

Multi-Organ Segmentation Over Partially Labeled Datasets With Multi-Scale Feature Abstraction

Fang

Yan

2020

IEEE Trans. Med. Imaging

165

View full text Add to dashboard Cite

show abstract

“…Supervised learning methods from the outset are subject to restrictions when applied to heterogeneous labeled data. Heterogeneous labeled data as defined by [10] is to be understood as partially labeled data. As a result, supervised training on heterogeneous data means reducing the number of available data samples for training, limiting the task's scope to a reduced set of classes, or conclusively an unfeasible training.…”

Section: Introductionmentioning

confidence: 99%

“…All data points are assigned a single, unambiguous class. This realization leads to an objective function that utilizes the mutually exclusive nature of ground truth masks in semantic segmentation [10,21].…”

Section: Introductionmentioning

confidence: 99%

“…Instead, this work proposes an approach for the frugal labeler and biomedical image recognition engineer to train neural networks for multi-class semantic segmentation (with U-Net) on heterogeneously labeled datasets. The novel combined objective function is presented, which represents a modified version of a sample dropping objective function [16,17], extended by the class-asymmetric (CA) objective function [10], to train on heterogeneous labeled datasets. The approach is implemented to train on heterogeneous labeled data according to training settings common in biomedical semantic segmentation: training on a heterogeneous labeled dataset, transfer learning for domain adaptation by introducing an additional class and training on multiple datasets with heterogeneous labels.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Methods for the frugal labeler: Multi-class semantic segmentation on heterogeneous labels

Schutera¹,

Rettenberger²,

Reischl³

2022

PLoS ONE

View full text Add to dashboard Cite

Deep learning increasingly accelerates biomedical research, deploying neural networks for multiple tasks, such as image classification, object detection, and semantic segmentation. However, neural networks are commonly trained supervised on large-scale, labeled datasets. These prerequisites raise issues in biomedical image recognition, as datasets are generally small-scale, challenging to obtain, expensive to label, and frequently heterogeneously labeled. Furthermore, heterogeneous labels are a challenge for supervised methods. If not all classes are labeled for an individual sample, supervised deep learning approaches can only learn on a subset of the dataset with common labels for each individual sample; consequently, biomedical image recognition engineers need to be frugal concerning their label and ground truth requirements. This paper discusses the effects of frugal labeling and proposes to train neural networks for multi-class semantic segmentation on heterogeneously labeled data based on a novel objective function. The objective function combines a class asymmetric loss with the Dice loss. The approach is demonstrated for training on the sparse ground truth of a heterogeneous labeled dataset, training within a transfer learning setting, and the use-case of merging multiple heterogeneously labeled datasets. For this purpose, a biomedical small-scale, multi-class semantic segmentation dataset is utilized. The heartSeg dataset is based on the medaka fish’s position as a cardiac model system. Automating image recognition and semantic segmentation enables high-throughput experiments and is essential for biomedical research. Our approach and analysis show competitive results in supervised training regimes and encourage frugal labeling within biomedical image recognition.

show abstract

“…Partially annotated datasets have been utilized previously. 8,9 In this paper, we propose a new weak supervision technique that fully utilizes partially annotated dataset. Throughout this paper, each DLD pattern is represented or painted in the following colors (CON:cyan, GGO:yellow, HCM:red, EMP:green, NOR:brown.…”

Section: Introductionmentioning

confidence: 99%

Weak supervision in convolutional neural network for semantic segmentation of diffuse lung diseases using partially annotated dataset

Suzuki

Yamagata

Yanagawa

et al. 2020

Medical Imaging 2020: Computer-Aided Diagnosis

View full text Add to dashboard Cite

Computer-aided diagnosis system for diffuse lung diseases (DLDs) is necessary for the objective assessment of the lung diseases. In this paper, we develop semantic segmentation model for 5 kinds of DLDs. DLDs considered in this work are consolidation, ground glass opacity, honeycombing, emphysema, and normal. Convolutional neural network (CNN) is one of the most promising technique for semantic segmentation among machine learning algorithms. While creating annotated dataset for semantic segmentation is laborious and time consuming, creating partially annotated dataset, in which only one chosen class is annotated for each image, is easier since annotators only need to focus on one class at a time during the annotation task. In this paper, we propose a new weak supervision technique that effectively utilizes partially annotated dataset. The experiments using partially annotated dataset composed 372 CT images demonstrated that our proposed technique significantly improved segmentation accuracy.

show abstract

Training a single multi-class convolutional segmentation network using multiple datasets with heterogeneous labels: preliminary results

Cited by 6 publications

References 3 publications

Multi-Organ Segmentation Over Partially Labeled Datasets With Multi-Scale Feature Abstraction

Multi-Organ Segmentation Over Partially Labeled Datasets With Multi-Scale Feature Abstraction

Methods for the frugal labeler: Multi-class semantic segmentation on heterogeneous labels

Weak supervision in convolutional neural network for semantic segmentation of diffuse lung diseases using partially annotated dataset

Contact Info

Product

Resources

About