Background: Patients with neurofibromatosis type 1 (NF1) develop benign (BPNST), premalignant atypical (ANF), and malignant (MPNST) peripheral nerve sheath tumors. Radiological differentiation of these entities is challenging. Therefore, we aimed to evaluate the value of a magnetic resonance imaging (MRI)-based radiomics machine-learning (ML) classifier for differentiation of these three entities of internal peripheral nerve sheath tumors in NF1 patients. Methods: MRI was performed at 3T in 36 NF1 patients (20 male; age: 31 ± 11 years). Segmentation of 117 BPNSTs, 17 MPNSTs, and 8 ANFs was manually performed using T2w spectral attenuated inversion recovery sequences. One hundred seven features per lesion were extracted using PyRadiomics and applied for BPNST versus MPNST differentiation. A 5-feature radiomics signature was defined based on the most important features and tested for signature-based BPNST versus MPNST classification (random forest [RF] classification, leave-one-patient-out evaluation). In a second step, signature feature expressions for BPNSTs, ANFs, and MPNSTs were evaluated for radiomics-based classification for these three entities. Results: The mean area under the receiver operator characteristic curve (AUC) for the radiomics-based BPNST versus MPNST differentiation was 0.94, corresponding to correct classification of on average 16/17 MPNSTs and 114/117 BPNSTs (sensitivity: 94%, specificity: 97%). Exploratory analysis with the eight ANFs revealed intermediate radiomic feature characteristics in-between BPNST and MPNST tumor feature expression. Conclusion: In this proof-of-principle study, ML using MRI-based radiomics characteristics allows sensitive and specific differentiation of BPNSTs and MPNSTs in NF1 patients. Feature expression of premalignant atypical tumors was distributed in-between benign and malignant tumor feature expressions, which illustrates biological plausibility of the considered radiomics characteristics.

Background: To examine the feasibility and safety of the SENSEI^® drop-in gamma probe for robot-assisted, prostate-specific membrane antigen (PSMA)-radioguided salvage surgery (RGS) in lymph node or local oligorecurrent prostate cancer (PCa), detected via PSMA positron emission tomography/computed tomography (PET/CT). Methods: The first thirteen patients with pelvic oligorecurrent PCa who underwent [^99mTc]Tc-PSMA-I&S RGS using the SENSEI^® drop-in gamma probe at the Martini-Klinik (February–June 2024) were retrospectively analyzed. Radioactivity measurements in counts per second (CPS) as absolute values or ratios (CPS of tumor specimens/mean CPS from the patients’ benign tissues) were correlated with preoperative imaging and pathological findings (benign/malignant, lesion size). Postoperative complete biochemical response (cBR) was defined as prostate-specific antigen (PSA) levels of <0.2 ng/mL. Results: Fifty-four specimens were removed from 13 patients, with nineteen (35%) containing PCa. All patients had one PSMA PET/CT-positive lesion, which were all detected intraoperatively. These lesions showed higher ex vivo CPS, CPS ratios, and larger cancer diameters than PSMA PET/CT-negative lesions (all p < 0.05). Cancer-containing specimens exhibited higher CPS and CPS ratios than benign tissues (median values of 45 vs. 3, and 9.9 vs. 1.0, both p < 0.001). In total, 12/13 (92%) patients achieved cBR. Conclusions: This device yielded excellent detection rates with good correlation to preoperative imaging and histological results without adverse events.