Loading
Prostate Cancer Diagnosis and Treatment / Advanced Radiotherapy Techniques · Journal article
Physical and Engineering Sciences in Medicine · September 8, 2026
Early or partial results. Treat as a signal, not a conclusion.
This is a retrospective algorithm development study demonstrating that a lightweight CNN can detect post-prostatectomy status from CT images with 86.5% accuracy and auROC 95.1%, substantially outperforming a segmentation volume threshold approach. The work identifies a systematic failure mode in a state-of-the-art segmentation tool (false prostate segments in 98.5% of post-prostatectomy patients) and proposes a technical fix, but requires external validation and integration testing before clinical deployment.
Retrospective algorithm development study with five-fold cross-validation. 542 prostate cancer patients from a single institution: 269 treated with robotic-assisted laparoscopic radical prostatectomy, 194 treated with radiation and/or androgen deprivation therapy only, 79 treatment-naive. Specific eligibility criteria not stated.. Intervention: Lightweight convolutional neural network trained to classify post-prostatectomy status from CT images. Compared with: Volume threshold approach applied to TotalSegmentator prostate segmentation volumes. n = 542. Single centre (location not specified).
TotalSegmentator produced false prostate segments in 98.5% of 269 post-prostatectomy patients Prostate segment volume was significantly smaller in post-RP cohort (12.1 ± 5.8 cm³ vs 22.8 ± 8.9 cm³ and 22.4 ± 10.9 cm³, p = 1.3e−17 and 2.1e−17) Volume threshold approach achieved RP detection accuracy 77.5 ± 1.3%, sensitivity 83.0 ± 3.9%, specificity 72.2 ± 3.5%, auROC 84.1 ± 2.3%
Safety was not reported in the material analysed. Check the source before drawing any conclusion about harm.
Clinicians and imaging informaticists developing automated CT analysis pipelines should be aware that commercial segmentation tools produce spurious prostate segments in nearly all post-prostatectomy patients. This CNN offers a potential automated correction mechanism, but external validation on independent datasets and integration into clinical workflows are necessary before adoption in clinical practice.
A single-centre algorithm development study demonstrating proof-of-concept for CNN-based prostatectomy detection on CT with reasonable accuracy, but lacking external validation, clinical outcomes data, and prospective deployment evidence.
As stated by the source record.
Quoted from the source exactly as published.
Clinicians and imaging informaticists developing automated CT analysis pipelines should be aware that commercial segmentation tools produce spurious prostate segments in nearly all post-prostatectomy patients. This CNN offers a potential automated correction mechanism, but external validation on independent datasets and integration into clinical workflows are necessary before adoption in clinical practice.
Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.
Abstract Extracting anatomic reference from computed tomography (CT) images is a crucial step in fully automated image analysis solutions for CT and hybrid imaging of prostate cancer. Several deep learning-based applications can be used to perform segmentation of different anatomical structures in CT, but they might produce a false prostate segment for post-treatment scans of patients treated with prostatectomy. In this study, our aim was to both systematically assess the performance of a state-of-the-art CT segmentation tool, TotalSegmentator, for post-prostatectomy patients and to investigate the potential of using a convolutional neural network (CNN) to automatically detect prostatectomy from CT images. We collected a dataset of CT images from 542 patients, 269 of which were treated with robotic-assisted laparoscopic radical prostatectomy (RP), 194 of which were treated with radiation and/or androgen deprivation therapy only, and 79 of which were treatment-naive. We used TotalSegmentator to perform multi-organ segmentation for all the patients, computed the volumes of the greatest connected components of the prostate segments, and studied the use of a cut-off threshold for the resulting volumes to detect RP with five-fold cross-validation. Additionally, we trained and evaluated a light-weight CNN for classifying patients treated with and without RP. According to our results, TotalSegmentator produced a false prostate segment for 98.5% patients treated with RP. The prostate segments were significantly smaller in the RP cohort than the other two cohorts (12.1 ± 5.8 cm $$^3$$ vs. 22.8 ± 8.9 cm $$^3$$ and 22.4 ± 10.9 cm $$^3$$, p -values: 1.3e−17 and 2.1e−17). The use of cut-off thresholds for TotalSegmentator’s prostate volumes resulted in RP detection accuracy of 77.5 ± 1.3%, sensitivity of 83.0 ± 3.9%, specificity of 72.2 ± 3.5%, precision of 74.4 ± 3.1%, and area under receiver operating characteristic curve (auROC) of 84.1 ± 2.3%. Conversely, our proposed CNN approach detected RP with accuracy of 86.5 ± 4.2%, sensitivity of 78.9 ± 12.5%, specificity of 93.5 ± 3.9%, precision of 92.7 ± 3.9%, and auROC of 95.1 ± 1.7%, outperforming the threshold approach in a statistically significant way according to DeLong’s tests (4 out of 5 p -values<0.045). To conclude, TotalSegmentator systematically produces false prostate segments with patients treated with RP but, by utilizing a CNN, RP can be detected automatically based on CT data only. This enables automated correction of TotalSegmentator masks. If developed further, our CNN method could provide a stand-alone application for identifying presence of prostatectomy efficiently without the need to consult treatment records and, consequently, assist in developing fully-automated image analysis tools.
Taken from the source record, never inferred. Follow any of these and new work involving them reaches your briefing.