Detection of prostate cancer using temporal sequences of ultrasound data: a large clinical feasibility study

Abstract

Purpose: This paper presents the results of a large study involving fusion prostate biopsies to demonstrate that temporal ultrasound can be used to accurately classify tissue labels identified in multi-parametric magnetic resonance imaging (mp-MRI) as suspicious for cancer.

Methods: We use deep learning to analyze temporal ultrasound data obtained from 255 cancer foci identified in mp-MRI. Each target is sampled in axial and sagittal planes. A deep belief network is trained to automatically learn the high-level latent features of temporal ultrasound data. A support vector machine classifier is then applied to differentiate cancerous versus benign tissue, verified by histopathology. Data from 32 targets are used for the training, while the remaining 223 targets are used for testing.

Results: Our results indicate that the distance between the biopsy target and the prostate boundary, and the agreement between axial and sagittal histopathology of each target impact the classification accuracy. In 84 test cores that are 5 mm or farther to the prostate boundary, and have consistent pathology outcomes in axial and sagittal biopsy planes, we achieve an area under the curve of 0.80. In contrast, all of these targets were labeled as moderately suspicious in mp-MR.

Conclusion: Using temporal ultrasound data in a fusion prostate biopsy study, we achieved a high classification accuracy specifically for moderately scored mp-MRI targets. These targets are clinically common and contribute to the high false-positive rates associated with mp-MRI for prostate cancer detection. Temporal ultrasound data combined with mp-MRI have the potential to reduce the number of unnecessary biopsies in fusion biopsy settings.

Keywords: Cancer diagnosis; Deep belief network; Deep learning; Prostate cancer; Temporal ultrasound data.

Fig. 1

a Training data set: 32 biopsy cores from 27 patients used for model generation. b Test data set: 223 biopsy cores from 138 patients used for analysis of the temporal US approach

Fig. 2

Flowchart of data division to training data and four subgroups of test data

Fig. 3

An illustration of the proposed framework for prostate cancer detection using temporal US data

Fig. 4

An illustration of the proposed feature visualization method

Fig. 5

Performance of the proposed method across Gleason scores in dataset: a D2 − A, b D2 − B

Fig. 6

Cancer probability maps overlaid on B-mode US image, along the projected needle path in the temporal US data and centered on the target. The ROIs for which the cancer likelihood are more than 70 % are colored in red; otherwise, they are colored as blue. Green boundary shows the segmented prostate in MRI projected in TRUS coordinates, dashed line shows needle path and the arrow pointer shows the target: a correctly identified benign core; b correctly identified cancerous core

Fig. 7

Hidden neuron activation probabilities (p) for 100 neurons and 2200 test data points after training. Black represents p = 0 and white, p = 1. Each row shows different neurons activations for a given input example, and each column shows a given neurons activations across many samples

Fig. 8

Differences of distributions between cancerous and benign tissue back projected in the input neurons: a corresponds to the first neuron in the third hidden layer; b corresponds to the sixth neuron in the third hidden layer. Results are shown in the frequency range of temporal ultrasound data analyzed in this paper. It is clear that frequencies between 0 and 2 Hz provide the most discriminative features for distinguishing cancerous and benign tissue