Deep learning for brain metastasis detection and segmentation in longitudinal MRI data. Issue 9 (22nd July 2022)

• Record Type: Journal Article
• Authors: Huang, Yixing; Bert, Christoph; Sommer, Philipp; Frey, Benjamin; Gaipl, Udo; Distel, Luitpold V.; Weissmann, Thomas; Uder, Michael; Schmidt, Manuel A.; Dörfler, Arnd; Maier, Andreas; Fietkau, Rainer; Putz, Florian
• Is Part Of: Medical physics. Volume 49:Issue 9(2022)
• Page Start: 5773
• Page End: 5786
• Publication Date: 2022-07-22
• Subjects: brain metastasis -- deep learning -- ensemble -- loss function -- MRI -- sensitivity specificity; Medical physics -- Periodicals; Medical physics; Geneeskunde; Natuurkunde; Toepassingen; Biophysics; Periodicals; Periodicals; Electronic journals; 610.153
• DOI: 10.1002/mp.15863
• Languages: English
• ISSNs: 0094-2405

Abstract

Abstract: Purpose: Brain metastases (BM) occur frequently in patients with metastatic cancer. Early and accurate detection of BM is essential for treatment planning and prognosis in radiation therapy. Due to their tiny sizes and relatively low contrast, small BM are very difficult to detect manually. With the recent development of deep learning technologies, several res earchers have reported promising results in automated brain metastasis detection. However, the detection sensitivity is still not high enough for tiny BM, and integration into clinical practice in regard to differentiating true metastases from false positives (FPs) is challenging. Methods: The DeepMedic network with the binary cross‐entropy (BCE) loss is used as our baseline method. To improve brain metastasis detection performance, a custom detection loss called volume‐level sensitivity–specificity (VSS) is proposed, which rates metastasis detection sensitivity and specificity at a (sub)volume level. As sensitivity and precision are always a trade‐off, either a high sensitivity or a high precision can be achieved for brain metastasis detection by adjusting the weights in the VSS loss without decline in dice score coefficient for segmented metastases. To reduce metastasis‐like structures being detected as FP metastases, a temporal prior volume is proposed as an additional input of DeepMedic. The modified network is called DeepMedic+ for distinction. Combining a high‐sensitivity VSS loss and a high specificity loss for DeepMedic+, the majority of true positive metastases are confirmed with high specificity, while additional metastases candidates in each patient are marked with high sensitivity for detailed expert evaluation. Results: Our proposed VSS loss improves the sensitivity of brain metastasis detection, increasing the sensitivity from 85.3% for DeepMedic with BCE to 97.5% for DeepMedic with VSS. Alternatively, the precision is improved from 69.1% for DeepMedic with BCE to 98.7% for DeepMedic with VSS. Comparing DeepMedic+ with DeepMedic with the same VSS loss, 44.4% of the FP metastases are reduced in the high‐sensitivity model and the precision reaches 99.6% for the high‐specificity model. The mean dice coefficient for all metastases is about 0.81. With the ensemble of the high‐sensitivity and high‐specificity models, on average only 1.5 FP metastases per patient need further check, while the majority of true positive metastases are confirmed. Conclusions: Our proposed VSS loss and temporal prior improve brain metastasis detection sensitivity and precision. The ensemble learning is able to distinguish high confidence true positive metastases from metastases candidates that require special expert review or further follow‐up, being particularly well‐fit to the requirements of expert support in real clinical practice. This facilitates metastasis detection and segmentation for neuroradiologists in diagnostic and radiation oncologists in therapeutic clinical applications.