AB010. Analyzing Response Assessment in Neuro-Oncology (RANO) response criteria in WHO grade III anaplastic astrocytomas in comparison to clinician evaluation: a case report.

BACKGROUND: Anaplastic astrocytoma [AA; World Health Organization (WHO) grade III] is a diffusely infiltrative astrocytic brain tumor with anaplasia and represents 3.3% of primary brain tumors. Overall, 5-year median survival can range from 22% to 50%, depending on various prognostic features, including the patient's age, tumor location and genetics, resection, etc. Given the higher grade and increased likelihood of transformation to WHO-grade IV tumors (glioblastomas), these tumors are generally treated aggressively upfront. Headache and seizures are the most common symptoms, occurring in about 50% of the cases. Other symptoms, including memory loss, motor weakness, language deficit, and cognitive and personality changes, occur in 20% of cases. Standard treatment involves surgical resection, radiotherapy, and chemotherapy, but treatment options are greatly limited for progression and recurrence. This paper highlights the case of a 48-year-old male who presents with chronic progressive cephalgia and a new-onset seizure. We review the diagnostic and therapeutic challenges associated with the treatment of AA. CASE DESCRIPTION: We describe a patient who presented with chronic progressive cephalgia, gradual right-sided weakness, an asymmetrical face, slurred speech, and a new-onset focal-to-bilateral seizure. A cranial magnetic resonance imaging revealed a mass in the left frontoparietal region, causing herniation of the cerebri to the right. The patient had a maximal tumor resection, and the histopathology showed tissue sections containing tumors that were infiltrative in the stroma, forming a diffuse pattern consisting of proliferation of oval, round, polygonal, spindle, pleomorphic oval nucleated cells, hyperchromatic, some nucleoli appearing prominent, and cytoplasmaeosinophilic. There were areas of stromal necrosis and mitosis [3/10 high power field (HPF)]. The pathology result was reported with AA. The patient underwent concomitant chemoradiation and followed oral chemotherapy with temozolomid. Subsequent imaging revealed a significant decrease in the tumor's size and a resolution of the compression of the brain parenchyma underneath. The Response Assessment in Neuro-Oncology (RANO) evaluation showed partial responses with good clinical improvement. CONCLUSIONS: The case presented an AA that was responsive to radiotherapy and temozolomid chemotherapy. Despite being rare, knowledge of this malignant tumor type and a multidisciplinary approach to case management are essential to optimizing treatment results.

Radiological evaluation of response in patients with locally advanced/metastatic soft tissue sarcoma treated with trabectedin.

Background: Trabectedin is an antineoplastic drug approved for patients (pts) with advanced soft tissue sarcomas (STS). Interestingly, the radiological evaluation of response during trabectedin therapy is peculiar. Methods: The aim of this single-center retrospective study is to analyze the concordance of response assessment according to RECIST compared with Choi criteria in patients with STS treated with trabectedin between 2009 and 2020 at Regina Elena National Cancer Institute in Rome. Results: We present the preliminary data collected in the last 2 months (mos) on 37 pts who received the diagnosis between 2015 and 2020, with a median age of 52.5 years (range 32-78). The median number of trabectedin cycles administered was four (range 2-50) for a median follow up of 5.83 months (range 1-60). Histological subtypes of STS were five (13.5%) leiomyosarcoma, 14 (37.8%) liposarcoma, nine (24.3%) undifferentiated pleomorphic sarcoma, three (8.1%) synovial sarcoma, and six (16.2%) other rare histological subtypes. Eight pts (21.6%) received trabectedin in the first line setting, 21 (56.8%) in the second line, and seven (18.9%) received it in subsequent lines. One pt received trabectedin as neoadjuvant therapy in a clinical trial (ISG-STS 1001). Median progression-free survival was 3.6 months (CI95% 2.7-4.6); median overall survival was 34.3 months (CI95% 0-75.4). The radiological responses were evaluated with both RECIST and Choi criteria; responses matched in 33 pts (89.2%) but not in four (10.8%). The best responses obtained according to RECIST criteria were two (5.4%) partial response (PR), 13 (35.1%) stable disease (SD), and 22 (59.5%) progressive disease (PD). Instead, two (5.4%), 13 (35.1%), and 22 (59.5%) pts obtained PR, SD, and PD respectively, according to Choi criteria. Cohen's kappa coefficient of concordance was 0.792 (p-value <0.002). A specialized radiologist performed all imaging examinations using a dedicated workstation in the same center. Conclusion: In this first analysis, the concordance between RECIST and Choi assessments demonstrates no statistically significant difference. Responses did not match for four pts. We are expanding the analysis to all pts included in the original cohort to confirm or deny these initial results.

Nuclear Medicine Imaging Techniques in Glioblastomas.

Glioblastomas are the most common primary malignant grade 4 tumors of the central nervous system (CNS). The treatment and management of such tumors requires a multidisciplinary approach and nuclear medicine techniques play an important role in this process. Glioblastoma, which recurs despite current treatments and becomes resistant to treatments, is among the tumors with the lowest survival rate, with a survival rate of approximately 8 months. Currently, the standard treatment of glioblastoma is adjuvant chemoradiotherapy after surgical resection. There have been many recent advances in the field of Nuclear Medicine in glioblastoma. PET scans are critical in determining tumor localization, pre-surgical planning, evaluation of post-treatment response and detection of recurrence. Advances in the treatment of glioblastoma and a better understanding of the biological characteristics of the disease have contributed to the development of nuclear medicine techniques. This review, in addition to other studies, is intended as a general imaging summary guide and includes some new expressions discovered in glioblastoma. This review discusses recent advances in nuclear medicine in glioblastoma.

Single versus multiple fraction stereotactic radiosurgery for medium-sized brain metastases (4-14 cc in volume): reducing or fractionating the radiosurgery dose?

Background and purpose: Stereotactic radiosurgery (SRS) of brain metastases (BM) and resection cavities is a widely used and effective treatment modality. Based on target lesion size and anatomical location, single fraction SRS (SF-SRS) or multiple fraction SRS (MF-SRS) are applied. Current clinical recommendations conditionally recommend either reduced dose SF-SRS or MF-SRS for medium-sized BM (2-2.9 cm in diameter). Despite excellent local control rates, SRS carries the risk of radionecrosis (RN). The purpose of this study was to assess the 12-months local control (LC) rate and 12-months RN rate of this specific patient population. Materials and methods: This single-center retrospective study included 54 patients with medium-sized intact BM (n=28) or resection cavities (n=30) treated with either SF-SRS or MF-SRS. Follow-up MRI was used to determine LC and RN using a modification of the "Brain Tumor Reporting and Data System" (BT-RADS) scoring system. Results: The 12-month LC rate following treatment of intact BM was 66.7% for SF-SRS and 60.0% for MF-SRS (p=1.000). For resection cavities, the 12-month LC rate was 92.9%% after SF-SRS and 46.2% after MF-SRS (p=0.013). For intact BM, RN rate was 17.6% for SF-SRS and 20.0% for MF-SRS (p=1.000). For resection cavities, RN rate was 28.6% for SF-SRS and 20.0% for MF-SRS (p=1.000). Conclusion: Patients with intact BM showed no statistically significant differences in 12-months LC and RN rate following SF-SRS or MF-SRS. In patients with resection cavities the 12-months LC rate was significantly better following SF-SRS, with no increase in the RNFS.

High-throughput sequencing of archival cerebrospinal fluid specimens defines B-lymphoblastic leukemia clonal composition.

Detailed characterization of the B-lymphoblastic leukemia (B-ALL) cells which invade the central nervous system (CNS) has been limited by practical challenges. To test whether the clonal composition of the cerebrospinal fluid (CSF) reflects the primary B-ALL tissue, we applied immunoglobulin (Ig) high-throughput sequencing (HTS) of archival CSF cytospin preparations from six patients with morphologically defined CNS involvement. We discovered that most CSF clones are detectable at some timepoint in the primary tissue, but that shifting clonal abundance is prevalent across tissue sites between diagnosis and relapse. Ig HTS of CSF cytospins may improve understanding of sanctuary site dissemination in B-ALL.

PSMA-PET/CT response after metastasis-directed radiotherapy of bone oligometastases in prostate cancer.

OBJECTIVE: Bone metastases are very common in advanced prostate cancer and can sensitively be detected utilizing PSMA-PET/CT. Therefore, our goal was to evaluate the suitability of PSMA-PET/CT-guided metastasis-directed external beam radiotherapy (MDT) as treatment option for patients with biochemical recurrence and oligometastatic bone lesions. MATERIALS & METHODS: We retrospectively examined 32 prostate cancer patients with biochemical recurrence and PSMA-positive oligometastatic disease limited to the bone (n = 1-3). A total of 49 bone lesions were treated with MDT. All patients received a post-radiotherapy PSMA-PET/CT-Scan. Changes in SUVmax, PSMA-positive tumor volume per lesion and PSA, as well as the correlation between the PET/CT-interval and SUVmax response were calculated. RESULTS: MDT lead to a SUVmax decrease in 46/49 (94%) of the lesions. The median relative decline of SUVmax was 60.4%, respectively. Based on PSMA-positive lesion volume with a SUV cut-off of 4, 46/49 (94%) of lesions showed complete response, two (4%) partial response and one lesion (2%) was stable on PSMA-PET/CT after MDT. Most of the treated patients (56.3%) showed an initial PSA decline at three months and a PSA nadir of median 0.14 ng/ml after a median time of 3.6 months after MDT. The median relative PSA change at three months after MDT was 3.9%. CONCLUSION: MDT is a very effective treatment modality for prostate cancer bone oligometastases and lesion response to MDT can be assessed using the (semi-)quantitative parameters SUVmax and PSMA-positive lesion volume with established SUV cut-offs.

Diffusion-weighted magnetic resonance imaging as an early prognostic marker of chemoradiotherapy response in squamous cell carcinoma of the anus: An individual patient data meta-analysis.

Background and purpose: Squamous cell carcinoma of the anus (SCCA) can recur after chemoradiotherapy (CRT). Early prediction of treatment response is crucial for individualising treatment. Existing data on radiological biomarkers is limited and contradictory. We performed an individual patient data meta-analysis (IPM) of four prospective trials investigating whether diffusion-weighted (DW) magnetic resonance imaging (MRI) in weeks two to three of CRT predicts treatment failure in SCCA. Material and methods: Individual patient data from four trials, including paired DW-MRI at baseline and during CRT, were combined into one dataset. The association between ADC volume histogram parameters and treatment failure (locoregional and any failure) was assessed using logistic regression. Pre-defined analysis included categorising patients into a change in the mean ADC of the delineated tumour volume above and below 20%. Results: The study found that among all included 142 patients, 11.3 % (n = 16) had a locoregional treatment failure. An ADC mean change of <20 % and >20 % resulted in a locoregional failure rate of 16.7 % and 8.0 %, respectively. However, no other ADC-based histogram parameter was associated with locoregional or any treatment failure. Conclusions: DW-MRI standard parameters, as an isolated biomarker, were not found to be associated with increased odds of treatment failure in SCCA in this IPM. Radiological biomarker investigations involve multiple steps and can result in heterogeneous data. In future, it is crucial to include radiological biomarkers in large prospective trials to minimize heterogeneity and maximize learning.

Treatment response assessment of acute pyelonephritis: A multi-reader DWI-based MRI approach.

PURPOSE: To evaluate the diagnostic accuracy of a structured reporting score (SRS) in treatment response assessment for acute pyelonephritis (APN) using a diffusion-weighted imaging (DWI) -based MRI approach. Additionally, we explored the influence of reader experience on the interpretation of SRS and DWI, including lesion conspicuity and measurements of Apparent Diffusion Coefficient (ADC) maps. METHODS: Follow-up DWI-based MRIs of 36 patients treated for APN between September 2021 and June 2023 were retrospectively reviewed by three readers. Follow-up blood inflammatory markers were used as reference standard. Treatment response was assessed using a structured reporting score (SRS). Each reader assigned a score from 1 to 3 to the "conspicuity" of the residual disease on DWI. Quantitative ADC measurements were compared with the Mann-Whitney U test. Descriptive statistics and Intraclass Correlation Coefficient (ICC) were calculated. RESULTS: The diagnostic accuracy of SRS was 80.6 %, 76.9 %, and 72.2 % for the Reader 1, 2, and 3 respectively. ICC decreased from 0.82 (Reader 1 and 2), to 0.68 when considering all readers. The average conspicuity varied between 2.3 and 2.7. ADC values were significantly higher in complete responders for Reader 1 and 2 (153.5-154.5 vs 107.7-116.2, p < 0.001). The ICC was good (0.89) for Reader 1 and 2 and moderate (0.60) when considering all readers. CONCLUSIONS: Treatment response of pyelonephritis can be accurately assessed by a DWI-based MRI, potentially avoiding unnecessary contrast agent administration and radiation exposure. SRS and DWI analysis showed a good inter-observer agreement but a certain learning curve may be necessary for less expert readers.

Prospective evaluation of quantitative response parameter in patients with Gastrointestinal Stroma Tumor undergoing tyrosine kinase inhibitor therapy-Impact on clinical outcome.

The purpose of this study was to determine if dual-energy CT (DECT) vital iodine tumor burden (ViTB), a direct assessment of tumor vascularity, allows reliable response assessment in patients with GIST compared to established CT criteria such as RECIST1.1 and modified Choi (mChoi). From 03/2014 to 12/2019, 138 patients (64 years [32-94 years]) with biopsy proven GIST were entered in this prospective, multi-center trial. All patients were treated with tyrosine kinase inhibitors (TKI) and underwent pre-treatment and follow-up DECT examinations for a minimum of 24 months. Response assessment was performed according to RECIST1.1, mChoi, vascular tumor burden (VTB) and DECT ViTB. A change in therapy management could be because of imaging (RECIST1.1 or mChoi) and/or clinical progression. The DECT ViTB criteria had the highest discrimination ability for progression-free survival (PFS) of all criteria in both first line and second line and thereafter treatment, and was significantly superior to RECIST1.1 and mChoi (p < .034). Both, the mChoi and DECT ViTB criteria demonstrated a significantly early median time-to-progression (both delta 2.5 months; both p < .036). Multivariable analysis revealed 6 variables associated with shorter overall survival: secondary mutation (HR = 4.62), polymetastatic disease (HR = 3.02), metastatic second line and thereafter treatment (HR = 2.33), shorter PFS determined by the DECT ViTB criteria (HR = 1.72), multiple organ metastases (HR = 1.51) and lower age (HR = 1.04). DECT ViTB is a reliable response criteria and provides additional value for assessing TKI treatment in GIST patients. A significant superior response discrimination ability for median PFS was observed, including non-responders at first follow-up and patients developing resistance while on therapy.

ACR Appropriateness Criteria® Pretreatment Evaluation and Follow-Up of Invasive Cancer of the Cervix: 2023 Update.

Cervical cancer is a common gynecological malignancy worldwide. Cervical cancer is staged based on the International Federation of Gynecology and Obstetrics (FIGO) classification system, which was revised in 2018 to incorporate radiologic and pathologic data. Imaging plays an important role in pretreatment assessment including initial staging and treatment response assessment of cervical cancer. Accurate determination of tumor size, local extension, and nodal and distant metastases is important for treatment selection and for prognostication. Although local recurrence can be diagnosed by physical examination, imaging plays a critical role in detection and follow-up of local and distant recurrence and subsequent treatment selection. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision process support the systematic analysis of the medical literature from peer reviewed journals. Established methodology principles such as Grading of Recommendations Assessment, Development, and Evaluation or GRADE are adapted to evaluate the evidence. The RAND/UCLA Appropriateness Method User Manual provides the methodology to determine the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where peer reviewed literature is lacking or equivocal, experts may be the primary evidentiary source available to formulate a recommendation.

Patient eligibility for trials with imaging response assessment at the time of molecular tumor board presentation.

PURPOSE: To assess the eligibility of patients with advanced or recurrent solid malignancies presented to a molecular tumor board (MTB) at a large precision oncology center for inclusion in trials with the endpoints objective response rate (ORR) or duration of response (DOR) based on Response Evaluation Criteria in Solid Tumors (RECIST version 1.1). METHODS: Prospective patients with available imaging at the time of presentation in the MTB were included. Imaging data was reviewed for objectifiable measurable disease (MD) according to RECIST v1.1. Additionally, we evaluated the patients with MD for representativeness of the identified measurable lesion(s) in relation to the overall tumor burden. RESULTS: 262 patients with different solid malignancies were included. 177 patients (68%) had MD and 85 (32%) had non-measurable disease (NMD) at the time point of MTB presentation in accordance with RECIST v1.1. MD was not representative of the overall tumor burden in eleven patients (6%). The main reasons for NMD were lesions with longest diameter shorter than 10 mm (22%) and non-measurable peritoneal carcinomatosis (18%). Colorectal cancer and malignant melanoma displayed the highest rates of MD (> 75%). In contrast, gastric cancer, head and neck malignancies, and ovarian carcinoma had the lowest rates of MD (< 55%). In case of MD, the measurable lesions were representative of the overall tumor burden in the vast majority of cases (94%). CONCLUSION: Approximately one third of cancer patients with advanced solid malignancies are not eligible for treatment response assessment in trials with endpoints ORR or DOR at the time of MTB presentation. The rate of patients eligible for trials with imaging endpoints differs significantly based on the underlying malignancy and should be taken under consideration during the planning of new precision oncology trials.

ACR Appropriateness Criteria® Pretreatment evaluation and follow-up of invasive cancer of the cervix: 2023 update

Cervical cancer is a common gynecological malignancy worldwide. Cervical cancer is staged based on the International Federation of Gynecology and Obstetrics (FIGO) classification system, which was revised in 2018 to incorporate radiologic and pathologic data. Imaging plays an important role in pretreatment assessment including initial staging and treatment response assessment of cervical cancer. Accurate determination of tumor size, local extension, and nodal and distant metastases is important for treatment selection and for prognostication. Although local recurrence can be diagnosed by physical examination, imaging plays a critical role in detection and follow-up of local and distant recurrence and subsequent treatment selection. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision process support the systematic analysis of the medical literature from peer reviewed journals. Established methodology principles such as Grading of Recommendations Assessment, Development, and Evaluation or GRADE are adapted to evaluate the evidence. The RAND/UCLA Appropriateness Method User Manual provides the methodology to determine the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where peer reviewed literature is lacking or equivocal, experts may be the primary evidentiary source available to formulate a recommendation.

Towards consistency in pediatric brain tumor measurements: Challenges, solutions, and the role of artificial intelligence-based segmentation.

MR imaging is central to the assessment of tumor burden and changes over time in neuro-oncology. Several response assessment guidelines have been set forth by the Response Assessment in Pediatric Neuro-Oncology (RAPNO) working groups in different tumor histologies; however, the visual delineation of tumor components using MRIs is not always straightforward, and complexities not currently addressed by these criteria can introduce inter- and intra-observer variability in manual assessments. Differentiation of non-enhancing tumors from peritumoral edema, mild enhancement from absence of enhancement, and various cystic components can be challenging; particularly given a lack of sufficient and uniform imaging protocols in clinical practice. Automated tumor segmentation with artificial intelligence (AI) may be able to provide more objective delineations, but rely on accurate and consistent training data created manually (ground truth). Herein, this paper reviews existing challenges and potential solutions to identifying and defining subregions of pediatric brain tumors (PBTs) that are not explicitly addressed by current guidelines. The goal is to assert the importance of defining and adopting criteria for addressing these challenges, as it will be critical to achieving standardized tumor measurements and reproducible response assessment in PBTs, ultimately leading to more precise outcome metrics and accurate comparisons among clinical studies.

Machine learning-based response assessment in patients with rectal cancer after neoadjuvant chemoradiotherapy: radiomics analysis for assessing tumor regression grade using T2-weighted magnetic resonance images.

PURPOSE: This study aimed to assess tumor regression grade (TRG) in patients with rectal cancer after neoadjuvant chemoradiotherapy (NCRT) through a machine learning-based radiomics analysis using baseline T2-weighted magnetic resonance (MR) images. MATERIALS AND METHODS: In total, 148 patients with locally advanced rectal cancer(T2-4 or N+) who underwent MR imaging at baseline and after chemoradiotherapy between January 2010 and May 2021 were included. A region of interest for each tumor mass was drawn by a radiologist on oblique axial T2-weighted images, and main features were selected using principal component analysis after dimension reduction among 116 radiomics and three clinical features. Among eight learning models that were used for prediction model development, the model showing best performance was selected. Treatment responses were classified as either good or poor based on the MR-assessed TRG (mrTRG) and pathologic TRG (pTRG). The model performance was assessed using the area under the receiver operating curve (AUROC) to classify the response group. RESULTS: Approximately 49% of the patients were in the good response (GR) group based on mrTRG (73/148) and 26.9% based on pTRG (28/104). The AUCs of clinical data, radiomics models, and combined radiomics with clinical data model for predicting mrTRG were 0.80 (95% confidence interval [CI] 0.73, 0.87), 0.74 (95% CI 0.66, 0.81), and 0.75(95% CI 0.68, 0.82), and those for predicting pTRG was 0.62 (95% CI 0.52, 0.71), 0.74 (95% CI 0.65, 0.82), and 0.79 (95% CI 0.71, 0.87). CONCLUSION: Radiomics combined with clinical data model using baseline T2-weighted MR images demonstrated feasible diagnostic performance in predicting both MR-assessed and pathologic treatment response in patients with rectal cancer after NCRT.

RAPNO efforts in Brain Tumour Outcomes.

Assessing treatment efficacy for brain tumours has evolved since its inception with the introduction of MacDonald's criteria, which pioneered the utility of imaging to determine an objective and quantifiable response to treatment. This criterion failed to distinguish pseudo response or progression from progression and did not account for non-enhancing disease therefore; the response assessment in neuro-oncology (RANO) working group was established to account for these limitations. Since, its commencement it has worked to determine response assessment for multiple tumours. As paediatric tumours exhibit heterogeneous and variable-enhancing characteristics, the response assessment in paediatric neuro-oncology (RAPNO) working group was formed to create separate criteria. Six response criteria have been published to date, and the article summarizes them.

Digital "flipbooks" for enhanced visual assessment of simple and complex brain tumors.

Typical longitudinal radiographic assessment of brain tumors relies on side-by-side qualitative visualization of serial magnetic resonance images (MRIs) aided by quantitative measurements of tumor size. However, when assessing slowly-growing tumors and/or complex tumors, side-by-side visualization and quantification may be difficult or unreliable. Whole-brain, patient-specific "digital flipbooks" of longitudinal scans are a potential method to augment radiographic side-by-side reads in clinical settings by enhancing the visual perception of changes in tumor size, mass effect, and infiltration across multiple slices over time. In this approach, co-registered, consecutive MRI scans are displayed in a slide deck, where one slide displays multiple brain slices of a single timepoint in an array (e.g. 3x5 "mosaic" view of slices). The flipbooks are viewed similar to an animated flipbook of cartoons/photos so that subtle radiographic changes are visualized via perceived motion when scrolling through the slides. Importantly, flipbooks can be created easily with free, open-source software. This article describes the step-by-step methodology for creating flipbooks and discusses clinical scenarios for which flipbooks are particularly useful. Example flipbooks are provided in the Online Supplemental Material.

Models using comprehensive, lesion-level, longitudinal [68Ga]Ga-DOTA-TATE PET-derived features lead to superior outcome prediction in neuroendocrine tumor patients treated with [177Lu]Lu-DOTA-TATE.

PURPOSE: Somatostatin receptor (SSTR) imaging features are predictive of treatment outcome for neuroendocrine tumor (NET) patients receiving peptide receptor radionuclide therapy (PRRT). However, comprehensive (all metastatic lesions), longitudinal (temporal variation), and lesion-level measured features have never been explored. Such features allow for capturing the heterogeneity in disease response to treatment. Furthermore, models combining these features are lacking. In this work we evaluated the predictive power of comprehensive, longitudinal, lesion-level 68GA-SSTR-PET features combined with a multivariate linear regression (MLR) model. METHODS: This retrospective study enrolled NET patients treated with [177Lu]Lu-DOTA-TATE and imaged with [68Ga]Ga-DOTA-TATE at baseline and post-therapy. All lesions were segmented, anatomically labeled, and longitudinally matched. Lesion-level uptake and variation in uptake were measured. Patient-level features were engineered and selected for modeling of progression-free survival (PFS). The model was validated via concordance index, patient classification (ROC analysis), and survival analysis (Kaplan-Meier and Cox proportional hazards). The MLR was benchmarked against single feature predictions. RESULTS: Thirty-six NET patients were enrolled and stratified into poor and good responders (PFS ≥ 25 months). Four patient-level features were selected, the MLR concordance index was 0.826, and the AUC was 0.88 (0.85 specificity, 0.81 sensitivity). Survival analysis led to significant patient stratification (p<.001) and hazard ratio (3⨯10-5). Lastly, in a benchmark study, the MLR modeling approach outperformed all the single feature predictors. CONCLUSION: Comprehensive, lesion-level, longitudinal 68GA-SSTR-PET analysis, combined with MLR modeling, leads to excellent predictions of PRRT outcome in NET patients, outperforming non-comprehensive, patient-level, and single time-point feature predictions. MESSAGE: Neuroendocrine tumor, peptide receptor radionuclide therapy, Somatostatin Receptor Imaging, Outcome Prediction, Treatment Response Assessment.