Learning Fuzzy Clustering for SPECT/CT Segmentation via Convolutional Neural Networks

TL;DR

This paper introduces a novel convolutional neural network-based segmentation method for QBSPECT/CT images, utilizing new loss functions inspired by Fuzzy C-means, achieving accurate results with limited annotated data.

Contribution

It proposes a new unsupervised loss function for CNNs based on Fuzzy C-means, enabling fast, robust, and semi-supervised segmentation of QBSPECT/CT images.

Findings

The method performs well on clinical datasets despite training on simulated images.

It achieves high Dice similarity coefficients for lesion and bone segmentation.

The approach is adaptable to different levels of supervision depending on data availability.

Abstract

Quantitative bone single-photon emission computed tomography (QBSPECT) has the potential to provide a better quantitative assessment of bone metastasis than planar bone scintigraphy due to its ability to better quantify activity in overlapping structures. An important element of assessing response of bone metastasis is accurate image segmentation. However, limited by the properties of QBSPECT images, the segmentation of anatomical regions-of-interests (ROIs) still relies heavily on the manual delineation by experts. This work proposes a fast and robust automated segmentation method for partitioning a QBSPECT image into lesion, bone, and background. We present a new unsupervised segmentation loss function and its semi- and supervised variants for training a convolutional neural network (ConvNet). The loss functions were developed based on the objective function of the classical Fuzzy C-means (FCM) algorithm. We conducted a comprehensive study to compare our proposed methods with ConvNets trained using supervised loss functions and conventional clustering methods. The Dice similarity coefficient (DSC) and several other metrics were used as figures of merit as applied to the task of delineating lesion and bone in both simulated and clinical SPECT/CT images. We experimentally demonstrated that the proposed methods yielded good segmentation results on a clinical dataset even though the training was done using realistic simulated images. A ConvNet-based image segmentation method that uses novel loss functions was developed and evaluated. The method can operate in unsupervised, semi-supervised, or fully-supervised modes depending on the availability of annotated training data. The results demonstrated that the proposed method provides fast and robust lesion and bone segmentation for QBSPECT/CT. The method can potentially be applied to other medical image segmentation applications.