Deep clustering for abdominal organ classification in ultrasound imaging
- 1 May 2023
- journal article
- research article
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 10 (03), 034502
- https://doi.org/10.1117/1.jmi.10.3.034502
Abstract
PurposeThe purpose of this study is to examine the utilization of unlabeled data for abdominal organ classification in multi-label (non-mutually exclusive classes) ultrasound images, as an alternative to the conventional transfer learning approach.ApproachWe present a new method for classifying abdominal organs in ultrasound images. Unlike previous approaches that only relied on labeled data, we consider the use of both labeled and unlabeled data. To explore this approach, we first examine the application of deep clustering for pretraining a classification model. We then compare two training methods, fine-tuning with labeled data through supervised learning and fine-tuning with both labeled and unlabeled data using semisupervised learning. All experiments were conducted on a large dataset of unlabeled images (nu = 84967) and a small set of labeled images (ns = 2742) comprising progressively 10%, 20%, 50%, and 100% of the images.ResultsWe show that for supervised fine-tuning, deep clustering is an effective pre-training method, with performance matching that of ImageNet pre-training using five times less labeled data. For semi-supervised learning, deep clustering pre-training also yields higher performance when the amount of labeled data is limited. Best performance is obtained with deep clustering pre-training combined with semi-supervised learning and 2742 labeled example images with an F1-score weighted average of 84.1%.ConclusionsThis method can be used as a tool to preprocess large unprocessed databases, thus reducing the need for prior annotations of abdominal ultrasound studies for the training of image classification algorithms, which in turn could improve the clinical use of ultrasound images.Keywords
This publication has 12 references indexed in Scilit:
- Voice-Assisted Image Labeling for Endoscopic Ultrasound Classification Using Neural NetworksIEEE Transactions on Medical Imaging, 2021
- DeepMCAT: Large-Scale Deep Clustering for Medical Image CategorizationPublished by Springer Science and Business Media LLC ,2021
- A Realistic Evaluation of Semi-Supervised Learning for Fine-Grained ClassificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2021
- Self-Supervised Contrastive Video-Speech Representation Learning for UltrasoundPublished by Springer Science and Business Media LLC ,2020
- Self-Supervised Visual Feature Learning With Deep Neural Networks: A SurveyIEEE Transactions on Pattern Analysis and Machine Intelligence, 2020
- Less is More: Simultaneous View Classification and Landmark Detection for Abdominal Ultrasound ImagesPublished by Springer Science and Business Media LLC ,2018
- Cross-Domain Self-Supervised Multi-task Feature Learning Using Synthetic ImageryPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2018
- Transfer Learning with Convolutional Neural Networks for Classification of Abdominal Ultrasound ImagesJournal of Digital Imaging, 2016
- Context Encoders: Feature Learning by InpaintingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- Perceived barriers in the use of ultrasound in developing countriesCritical Ultrasound Journal, 2015