Delineation of the Prostate Bed: The “Invisible Target” Is Still an Issue?

Latorzeff, I.; Sargos, P.; Loos, G.; Supiot, S.; Guérif, S.; Carrié, C.

doi:10.3389/fonc.2017.00108

Cited by 19 publications

(13 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1, the prostate bed, an anatomical region in the male pelvis situated between the bladder and rectum, mainly consists of the residual prostatic tissue after the removal of the prostate gland and some adjacent volume of the bladder. It is not an intact structure with boundary like the prostate gland so often referred to as a "virtual" volume [1,3,4] in the literature. This made the segmentation of the prostate bed a unique problem and much harder than the segmentation of most other structures.…”

mentioning

confidence: 99%

Asymmetrical Multi-task Attention U-Net for the Segmentation of Prostate Bed in CT Image

Wang

et al. 2020

Medical Image Computing and Computer Assisted Intervention – MICCAI 2020

View full text Add to dashboard Cite

Segmentation of the prostate bed, the residual tissue after the removal of the prostate gland, is an essential prerequisite for post-prostatectomy radiotherapy but also a challenging task due to its non-contrast boundaries and highly variable shapes relying on neighboring organs. In this work, we propose a novel deep learning-based method to automatically segment this "invisible target". As the main idea of our design, we expect to get reference from the surrounding normal structures (bladder&rectum) and take advantage of this information to facilitate the prostate bed segmentation. To achieve this goal, we first use a U-Net as the backbone network to perform the bladder&rectum segmentation, which serves as a low-level task that can provide references to the high-level task of the prostate bed segmentation. Based on the backbone network, we build a novel attention network with a series of cascaded attention modules to further extract discriminative features for the high-level prostate bed segmentation task. Since the attention network has onesided dependency on the backbone network, simulating the clinical workflow to use normal structures to guide the segmentation of radiotherapy target, we name the final composition model asymmetrical multi-task attention U-Net. Extensive experiments on a clinical dataset consisting of 186 CT images demonstrate the effectiveness of this new design and the superior performance of the model in comparison to the conventional atlas-based methods for prostate bed segmentation. The source code is publicly available at https://github.com/superxuang/amta-net.

show abstract

mentioning

confidence: 99%

Asymmetrical Multi-task Attention U-Net for the Segmentation of Prostate Bed in CT Image

Wang

et al. 2020

Medical Image Computing and Computer Assisted Intervention – MICCAI 2020

View full text Add to dashboard Cite

show abstract

“…Compared to EORTC and FROGG guidelines, Radiation Therapy Oncology Group delineates a volume of prostate bed CTV encompassing a larger volume of bladder, maintaining a significantly lower exposure of rectum and mesorectal fascia. 37 , 38 As reported by Ko et al, 39 the vesico-urethral anastomosis represents the most frequent site of relapse, and it must be encompassed with posterior bladder wall in prostate bed CTV, leading to high exposure of normal bladder tissue, with an increased risk both in terms of frequency and severity of acute and late GU toxicities.…”

Section: Discussionmentioning

confidence: 95%

Hypofractionated postoperative helical tomotherapy in prostate cancer: a mono-institutional report of toxicity and clinical outcomes

Cuccia

Mortellaro²,

Serretta

et al. 2018

CMAR

View full text Add to dashboard Cite

PurposeThis is a mono-institutional study of acute and late toxicities and early biochemical control of a retrospective series of 75 prostate cancer patients treated with moderate postoperative hypofractionation delivered by helical tomotherapy (HT).Patients and methodsFrom April 2013 to June 2017, 75 patients received adjuvant (n=37) or salvage (n=38) treatment, delivering to prostate bed a total dose of 63.8 Gy (equivalent dose in 2-Gy fractions=67.4 Gy) using 2.2 Gy fractions. Whole-pelvis irradiation was performed in 63% of cases (median dose, 49.3 Gy; range, 48–55.1 Gy). Concurrent hormonal therapy was administered in 46% of cases. Common Terminology Criteria for Adverse Events (version 4.0) was adopted for acute and late genitourinary (GU) and gastrointestinal (GI) toxicity evaluations. Biochemical progression was defined as PSA level increase of ≥0.2 or more above the postoperative radiotherapy (RT) nadir.ResultsAcute GU toxicities were as follows: G1 in 46% and G2 in 4%, detecting no G≥3 events. For GI toxicity, we recorded G1 in 36% and G2 in 18%. With a median follow-up of 30 months (range, 12–58 months), we found late toxicity G2 GI in 6.6% and G≥2 GU in 5.3%, including two patients who underwent surgical incontinence correction. Acute GI≥2 toxicity and diabetes were found to be predictive of late GI≥2 toxicity (P=0.04 and P=0.0019). Actuarial 2- and 3-year biochemical recurrence-free survivals were 88% and 73%, respectively, for the entire population.ConclusionIn our experience, moderate hypofractionated postoperative RT with HT was feasible and safe, with reports of low incidence of toxicity and promising biochemical control rates.

show abstract

“…PET imaging begins 3-5 minutes after the injection of radiotracer. Scanning from the midthigh to the skull base (caudal to cranial) optimizes the target-to-background tissue ratio by maximizing agreement regarding the size of the pelvic radiation field in patients with recurrent disease, and the presence of extrapelvic metastatic disease typically excludes patients from salvage radiation therapy (5,6). Therefore, identification of the extent of pelvic disease and detection of extrapelvic metastases significantly affect plans for subsequent salvage radiation therapy (7).…”

Section: Facbc Imaging Characteristicsmentioning

confidence: 99%

Review of ¹⁸F-Fluciclovine PET for Detection of Recurrent Prostate Cancer

et al. 2019

View full text Add to dashboard Cite

Fluorine 18 (18 F) fluciclovine (anti-1-amino-3-18 F-fluorocyclobutane-1-carboxylic acid [FACBC]) is a radiolabeled amino acid analog that takes advantage of the amino acid transport upregulation in several types of cancer cells. FACBC is taken up to a greater extent in prostate cancer cells than in surrounding normal tissue, providing an opportunity for its use in cases of this common cancer. In 2016, the U.S. Food and Drug Administration found the accuracy of FACBC PET to be superior to that of other molecular imaging techniques and subsequently granted approval for its use in PET of recurrent prostate cancer. As FACBC is an 18 F radiotracer, an on-site cyclotron is not required for its production. This feature enables the widespread clinical availability of this agent and, in turn, an opportunity for improved patient care. The clinical pharmacology and imaging features of FACBC are reviewed, and the role of this agent in the imaging of recurrent prostate cancer, within the context of research that supports its effectiveness, is discussed. The administration of and image acquisition facilitated by using FACBC, as compared with 18 F fluorodeoxyglucose, which is more widely used, are described. In addition, the criteria for interpreting FACBC imaging findings are outlined, with emphasis on common causes of false-positive and false-negative findings. ©

show abstract

Delineation of the Prostate Bed: The “Invisible Target” Is Still an Issue?

Cited by 19 publications

References 39 publications

Asymmetrical Multi-task Attention U-Net for the Segmentation of Prostate Bed in CT Image

Asymmetrical Multi-task Attention U-Net for the Segmentation of Prostate Bed in CT Image

Hypofractionated postoperative helical tomotherapy in prostate cancer: a mono-institutional report of toxicity and clinical outcomes

Review of ¹⁸F-Fluciclovine PET for Detection of Recurrent Prostate Cancer

Contact Info

Product

Resources

About

Delineation of the Prostate Bed: The “Invisible Target” Is Still an Issue?

Cited by 19 publications

References 39 publications

Asymmetrical Multi-task Attention U-Net for the Segmentation of Prostate Bed in CT Image

Asymmetrical Multi-task Attention U-Net for the Segmentation of Prostate Bed in CT Image

Hypofractionated postoperative helical tomotherapy in prostate cancer: a mono-institutional report of toxicity and clinical outcomes

Review of 18F-Fluciclovine PET for Detection of Recurrent Prostate Cancer

Contact Info

Product

Resources

About

Review of ¹⁸F-Fluciclovine PET for Detection of Recurrent Prostate Cancer