[Interest using 3D ultrasound and MRI fusion biopsy for prostate cancer detection]

A temporal enhanced semi-supervised training framework for needle segmentation in 3D ultrasound images

Objective.Automated biopsy needle segmentation in 3D ultrasound images can be used for biopsy navigation, but it is quite challenging due to the low ultrasound image resolution and interference similar to the needle appearance. For 3D medical image segmentation, such deep learning networks as convolutional neural network and transformer have been investigated. However, these segmentation methods require numerous labeled data for training, have difficulty in meeting the real-time segmentation requirement and involve high memory consumption.Approach.In this paper, we have proposed the temporal information-based semi-supervised training framework for fast and accurate needle segmentation. Firstly, a novel circle transformer module based on the static and dynamic features has been designed after the encoders for extracting and fusing the temporal information. Then, the consistency constraints of the outputs before and after combining temporal information are proposed to provide the semi-supervision for the unlabeled volume. Finally, the model is trained using the loss function which combines the cross-entropy and Dice similarity coefficient (DSC) based segmentation loss with mean square error based consistency loss. The trained model with the single ultrasound volume input is applied to realize the needle segmentation in ultrasound volume.Main results.Experimental results on three needle ultrasound datasets acquired during the beagle biopsy show that our approach is superior to the most competitive mainstream temporal segmentation model and semi-supervised method by providing higher DSC (77.1% versus 76.5%), smaller needle tip position (1.28 mm versus 1.87 mm) and length (1.78 mm versus 2.19 mm) errors on the kidney dataset as well as DSC (78.5% versus 76.9%), needle tip position (0.86 mm versus 1.12 mm) and length (1.01 mm versus 1.26 mm) errors on the prostate dataset.Significance.The proposed method can significantly enhance needle segmentation accuracy by training with sequential images at no additional cost. This enhancement may further improve the effectiveness of biopsy navigation systems.

MRI/US fusion-guided biopsy: performing exclusively targeted biopsies for the early detection of prostate cancer

PURPOSE

The aim of this study was to validate the role of MR/Ultrasound Fusion-Guided Targeted Biopsy as a first diagnostic modality in subjects with clinical suspicion of prostate cancer (PCa).

MATERIALS AND METHODS

108 men (age range 46-78 years) with clinical suspicion for PCa (PSA > 4 ng/mL) underwent multiparametric MRI of the prostate (mpMRI) and, when suspicious lesion were found (according to the PIRADSv2 scoring system), targeted biopsy was performed. All patients without significant alteration patterns at mpMRI have been referred for follow-up at 1 year.

RESULTS

91/108 patients showed on the mpMRI highly suspicious lesions (PIRADS 4 and 5); the remaining 17/108 patients revealed no significant alteration consistent with PCa (PIRADS 3). Among the first group of patients, 58/91 proved to be positive for PCa on the pathology report: 24 patients had a Gleason Score (GS) 6 (3 + 3); 18 patients GS 7 of which 7 (3 + 4) and 11 (4 + 3); 14 patients GS 8 (4 + 4); two patients GS 9 (5 + 4); 33 proved to be negative. Overall cancer detection rate (CDR) was 63%. However, the CDR rises significantly, up to 77%, after the 53 initial consecutive biopsies that were performed (p < 0,05) and thus identified as part of the learning curve. Patients of the second group (17/108) have been followed with serial PSA assessments, clinical reevaluation, and follow-up mpMRI.

CONCLUSION

Performing exclusively targeted MR/Ultrasound Fusion-Guided biopsies for the diagnosis of PCa in patients with suspicious PSA levels (> 4 ng/mL) increases the detection rate of clinically significant cancer, changing both the therapeutic options and the prognosis.