Radiomics of Intrahepatic Cholangiocarcinoma and Peritumoral Tissue Predicts Postoperative Survival: Development of a CT-Based Clinical-Radiomic Model.

BACKGROUND: For many tumors, radiomics provided a relevant prognostic contribution. This study tested whether the computed tomography (CT)-based textural features of intrahepatic cholangiocarcinoma (ICC) and peritumoral tissue improve the prediction of survival after resection compared with the standard clinical indices. METHODS: All consecutive patients affected by ICC who underwent hepatectomy at six high-volume centers (2009-2019) were considered for the study. The arterial and portal phases of CT performed fewer than 60 days before surgery were analyzed. A manual segmentation of the tumor was performed (Tumor-VOI). A 5-mm volume expansion then was applied to identify the peritumoral tissue (Margin-VOI). RESULTS: The study enrolled 215 patients. After a median follow-up period of 28 months, the overall survival (OS) rate was 57.0%, and the progression-free survival (PFS) rate was 34.9% at 3 years. The clinical predictive model of OS had a C-index of 0.681. The addition of radiomic features led to a progressive improvement of performances (C-index of 0.71, including the portal Tumor-VOI, C-index of 0.752 including the portal Tumor- and Margin-VOI, C-index of 0.764, including all VOIs of the portal and arterial phases). The latter model combined clinical variables (CA19-9 and tumor pattern), tumor indices (density, homogeneity), margin data (kurtosis, compacity, shape), and GLRLM indices. The model had performance equivalent to that of the postoperative clinical model including the pathology data (C-index of 0.765). The same results were observed for PFS. CONCLUSIONS: The radiomics of ICC and peritumoral tissue extracted from preoperative CT improves the prediction of survival. Both the portal and arterial phases should be considered. Radiomic and clinical data are complementary and achieve a preoperative estimation of prognosis equivalent to that achieved in the postoperative setting.

The role of preoperative [11C]methionine PET in defining tumor-related epilepsy and predicting short-term postoperative seizure control in temporal lobe low-grade gliomas.

OBJECTIVE: Surgery is the mainstay of treatment for low-grade glioma (LGG)-related epilepsy. However, the goal of achieving both oncological radical resection and seizure freedom can be challenging. PET with [11C]methionine (MET) has been recently introduced in clinical practice for the management of patients with LGGs, not only to monitor the response to treatments, but also as a preoperative tool to define the metabolic tumor extent and to predict tumor grading, type, and prognosis. Still, its role in defining tumor-related epilepsy and postoperative seizure outcomes is limited. The aim of this preliminary study was to investigate the role of MET PET in defining preoperative seizure characteristics and short-term postoperative seizure control in a cohort of patients with newly diagnosed temporal lobe low-grade gliomas (tLGGs). METHODS: Patients with newly diagnosed and histologically proven temporal lobe grade 2/3 gliomas (2021 WHO CNS tumor classification) who underwent resection at the authors' institution between July 2011 and March 2021 were included in this retrospective study. MET PET images were acquired, fused with MRI scans, and qualitatively and semiquantitatively analyzed. Any eventual PET/MRI involvement of the temporomesial area, seizure characteristics, and 1-year seizure outcomes were reported. RESULTS: A total of 52 patients with tLGGs met the inclusion criteria. MET PET was positive in 41 (79%) patients, with a median metabolic tumor volume of 14.56 cm3 (interquartile range [IQR] 6.5-28.2 cm3). The median maximum and mean tumor-to-background ratio (TBRmax, TBRmean) were 2.24 (IQR 1.58-2.86) and 1.53 (IQR 1.37-1.70), respectively. The metabolic tumor volume was found to be related to the presence of seizures at disease onset, but only in noncodeleted tumors (p = 0.014). Regarding patients with uncontrolled seizures at surgery, only the temporomesial area PET involvement showed a statistical correlation both in the univariate (p = 0.058) and in the multivariate analysis (p = 0.030). At 1-year follow-up, seizure control was correlated with MET PET-derived semiquantitative data. Particularly, higher TBRmax (p = 0.0192) and TBRmean (p = 0.0128) values were statistically related to uncontrolled seizures 1 year after surgery. CONCLUSIONS: This preliminary study suggests that MET PET may be used as a preoperative tool to define seizure characteristics and outcomes in patients with tLGGs. These findings need to be further validated in larger series with longer epileptological follow-ups.

Baseline circulating tumour DNA and interim PET predict response in relapsed/refractory classical Hodgkin lymphoma.

Reliable biomarkers for early identification of treatment failure in relapsed/refractory (r/r) classical Hodgkin lymphoma (cHL) are lacking. Circulating tumour DNA (ctDNA) profiling has emerged as a powerful predictive and prognostic tool in several haemopoietic and non-haemopoietic malignancies and may guide rational treatment choices in r/r cHL. To assess the predictive and prognostic value of ctDNA, we performed a retrospective analysis on 55 r/r cHL patients treated with the bendamustine, gemcitabine and vinorelbine (BEGEV) regimen and additionally evaluated the potential utility of integrating ctDNA with interim [18 F]-FDG positron emission tomography (iPET). Baseline ctDNA genotyping in r/r cHL mirrored gene mutations and pathways involved in newly diagnosed cHL. We found that baseline ctDNA quantification and serial ctDNA monitoring have prognostic value in r/r cHL receiving salvage chemotherapy. Lastly, integrating ctDNA quantification with iPET evaluation may improve the early identification of patients at high risk of failing standard salvage therapy, who may benefit from an early switch to immunotherapeutic agents. Collectively, our results support the implementation of non-invasive methods to detect minimal residual disease in recurrent cHL and justify its prospective evaluation in appropriately designed clinical trials.

Dual adversarial deconfounding autoencoder for joint batch-effects removal from multi-center and multi-scanner radiomics data.

Medical imaging represents the primary tool for investigating and monitoring several diseases, including cancer. The advances in quantitative image analysis have developed towards the extraction of biomarkers able to support clinical decisions. To produce robust results, multi-center studies are often set up. However, the imaging information must be denoised from confounding factors-known as batch-effect-like scanner-specific and center-specific influences. Moreover, in non-solid cancers, like lymphomas, effective biomarkers require an imaging-based representation of the disease that accounts for its multi-site spreading over the patient's body. In this work, we address the dual-factor deconfusion problem and we propose a deconfusion algorithm to harmonize the imaging information of patients affected by Hodgkin Lymphoma in a multi-center setting. We show that the proposed model successfully denoises data from domain-specific variability (p-value < 0.001) while it coherently preserves the spatial relationship between imaging descriptions of peer lesions (p-value = 0), which is a strong prognostic biomarker for tumor heterogeneity assessment. This harmonization step allows to significantly improve the performance in prognostic models with respect to state-of-the-art methods, enabling building exhaustive patient representations and delivering more accurate analyses (p-values < 0.001 in training, p-values < 0.05 in testing). This work lays the groundwork for performing large-scale and reproducible analyses on multi-center data that are urgently needed to convey the translation of imaging-based biomarkers into the clinical practice as effective prognostic tools. The code is available on GitHub at this https://github.com/LaraCavinato/Dual-ADAE .

The potential role of osteoporosis in unspecific [18F]PSMA-1007 bone uptake.

AIM: Unspecific bone uptake is one of the main limitations of PET imaging with some PSMA-targeting radiopharmaceuticals, especially with [18F]PSMA-1007. We explored the potential association between osteoporosis and the occurrence of unspecific [18F]PSMA-1007 bone uptake investigating markers which might correlate with bone mineral density. MATERIALS AND METHODS: We retrospectively analyzed treatment-naïve patients with a confirmed diagnosis of prostate adenocarcinoma who underwent staging [18F]PSMA-1007 positron emission tomography (PET). Qualitative image analysis was performed independently by three experienced nuclear medicine physicians. Patients were divided in two groups according to the presence/absence of unspecific bone uptake. Clinical information, blood count parameters (assessed within 3 months to the PET scan), body mass index (BMI), and bone density as estimated by computed tomography were collected. The Kruskal-Wallis and t-test were used to compare parameters. RESULTS: We analyzed 77 patients: 29 of them (38%) had unspecific bone uptake at [18F]PSMA-1007 PET, most commonly in the pelvic bones (69%) and ribs (62%). We did not find any significant difference in clinical parameters in the two groups. In patients with unspecific bone uptake, white blood cell, and neutrophil counts were significantly higher; in the same group, we observed lower values of BMI and bone density, although not statistically different. CONCLUSIONS: We observed unspecific bone uptake on [18F]PSMA-1007 PET in more than 1/3 of patients. In this exploratory analysis, we found a significant correlation between blood count parameters and unspecific [18F]PSMA-1007 bone uptake. We may speculate that [18F]PSMA-1007 unspecific bone uptake could be associated with osteoporosis. This hypothesis needs to be further investigated in larger populations and exploring more specific markers of osteoporosis.

The prognostic power of [11C]methionine PET in IDH-wildtype diffuse gliomas with lower-grade histological features: venturing beyond WHO classification.

PURPOSE: IDH-wildtype (IDH-wt) diffuse gliomas with histological features of lower-grade gliomas (LGGs) are rare and heterogeneous primary brain tumours. [11C]Methionine (MET) positron emission tomography (PET) is commonly used to evaluate glial neoplasms at diagnosis. The present study aimed to assess the prognostic value of MET PET in newly diagnosed, treatment naïve IDH-wt gliomas with histological features of LGGs. METHODS: Patients with a histological diagnosis of IDH-wt LGG who underwent preoperative (< 100 days) MET PET/CT and surgery were retrospectively included. Qualitative and semi-quantitative analyses of MET PET images were performed. Progression-free survival (PFS) and overall survival (OS) were analysed by Kaplan-Meier curves. Cox proportional-hazards regression was used to test the association of imaging and clinical data to PFS and OS. RESULTS: We included 48 patients (M:F = 25:23; median age 55). 39 lesions were positive and 9 negative at MET PET. Positive MET PET was significantly associated with shorter median PFS (15.7 months vs. not reached, p = 0.0146) and OS time (32.6 months vs. not reached, p = 0.0253). Incomplete surgical resection and higher TBRmean values were independent predictors of shorter PFS on multivariate analysis (p < 0.001 for both). Higher tumour grade and incomplete surgical resection were independent predictors of OS at multivariate analysis (p = 0.027 and p = 0.01, respectively). CONCLUSION: MET PET is useful for the prognostic stratification of patients with IDH-wt glial neoplasms with histological LGGs features. Considering their huge biological heterogeneity, the combination of MET PET and molecular analyses may help to improve the prognostic accuracy in these diffuse gliomas subset and influence therapeutic choices accordingly.

Radiomic Analysis of Intrahepatic Cholangiocarcinoma: Non-Invasive Prediction of Pathology Data: A Multicenter Study to Develop a Clinical-Radiomic Model.

Standard imaging cannot assess the pathology details of intrahepatic cholangiocarcinoma (ICC). We investigated whether CT-based radiomics may improve the prediction of tumor characteristics. All consecutive patients undergoing liver resection for ICC (2009-2019) in six high-volume centers were evaluated for inclusion. On the preoperative CT, we segmented the ICC (Tumor-VOI, i.e., volume-of-interest) and a 5-mm parenchyma rim around the tumor (Margin-VOI). We considered two types of pathology data: tumor grading (G) and microvascular invasion (MVI). The predictive models were internally validated. Overall, 244 patients were analyzed: 82 (34%) had G3 tumors and 139 (57%) had MVI. For G3 prediction, the clinical model had an AUC = 0.69 and an Accuracy = 0.68 at internal cross-validation. The addition of radiomic features extracted from the portal phase of CT improved the model performance (Clinical data+Tumor-VOI: AUC = 0.73/Accuracy = 0.72; +Tumor-/Margin-VOI: AUC = 0.77/Accuracy = 0.77). Also for MVI prediction, the addition of portal phase radiomics improved the model performance (Clinical data: AUC = 0.75/Accuracy = 0.70; +Tumor-VOI: AUC = 0.82/Accuracy = 0.73; +Tumor-/Margin-VOI: AUC = 0.82/Accuracy = 0.75). The permutation tests confirmed that a combined clinical-radiomic model outperforms a purely clinical one (p < 0.05). The addition of the textural features extracted from the arterial phase had no impact. In conclusion, the radiomic features of the tumor and peritumoral tissue extracted from the portal phase of preoperative CT improve the prediction of ICC grading and MVI.

Imaging Correlates between Headache and Breast Cancer: An [18F]FDG PET Study.

This study aimed to examine brain metabolic patterns on [18F]Fluorodeoxyglucose ([18F]FDG) positron emission tomography (PET) in breast cancer (BC), comparing patients with tension-type headache (TTH), migraine (MiG), and those without headache. Further association with BC response to neoadjuvant chemotherapy (NAC) was explored. In this prospective study, BC patients eligible for NAC performed total-body [18F]FDG PET/CT with a dedicated brain scan. A voxel-wise analysis (two-sample t-test) and a multiple regression model were used to compare brain metabolic patterns among TTH, MiG, and no-headache patients and to correlate them with clinical covariates. A single-subject analysis compared each patient's brain uptake before and after NAC with a healthy control group. Primary headache was diagnosed in 39/46 of BC patients (39% TTH and 46% MiG). TTH patients exhibited hypometabolism in specific brain regions before NAC. TTH patients with a pathological complete response (pCR) to NAC showed hypermetabolic brain regions in the anterior medial frontal cortex. The correlation between tumor uptake and brain metabolism varied before and after NAC, suggesting an inverse relationship. Additionally, the single-subject analysis revealed that hypometabolic brain regions were not present after NAC. Primary headache, especially MiG, was associated with a better response to NAC. These findings suggest complex interactions between BC, headache, and hormonal status, warranting further investigation in larger prospective cohorts.

Radioisotope-Guided Excision of Mediastinal Lymph Nodes in Patients with Non-Small Cell Lung Carcinoma: Feasibility and Clinical Impact.

BACKGROUND: Intraoperative localisation of nodal disease in non-small cell lung cancer (NSCLC) can be challenging. Lymph node localisation via radiopharmaceuticals is used in many conditions; we tested the feasibility of this approach in NSCLC. METHODS: NSCLC patients were prospectively recruited. Intraoperative peri-tumoral injections of [99mTc]Tc-albumin nanocolloids were performed, followed by removing the tumour and locoregional lymph nodes. These were examined ex vivo with a gamma probe and labelled sentinel lymph nodes (SLNs) if they showed any activity or non-sentinel lymph nodes (nSLNs) if they did not. Thereafter, the surgical field was scanned with the probe; any further radioactive lymph node was removed and labelled as "extra" SLNs (eSLNs). All specimens were sent to histology, and metastatic status was recorded. RESULTS: 48 patients were enrolled, and 290 nodal stations were identified: 179 SLNs, 87 nSLNs, and 24 eSLNs. A total of 44 nodal metastases were identified in 22 patients, with 36 of them (82%) located within SLNs. Patients with nSLNs metastases had at least a co-existing positive SLN. No metastases were found in eSLNs. CONCLUSIONS: The technique shows high sensitivity for intraoperative nodal metastases identification. This information could allow selective lymphadenectomies in low-risk patients or more aggressive approaches in high-risk patients.

PSMA guided approach for bIoCHEmical relapse after prostatectomy- (PSICHE) trial (NCT05022914). Detection rate and treatment decision after 68Ga-PSMA PET/CT within a prospective study.

BACKGROUND: Ultrasensitive imaging has been demonstrated to influence biochemical relapse treatment. PSICHE is a multicentric prospective study, aimed at exploring detection rate with 68Ga-PSMA-11 positron emission tomography/computed tomography (PET/CT) and outcomes with a predefined treatment algorithm tailored to the imaging. METHODS: Patients affected by biochemical recurrence after surgery (prostate specific antigen [PSA] > 0.2 < 1 ng/mL) underwent staging with 68Ga-PSMA PET/CT. Management followed this treatment algorithm accordingly with PSMA results: prostate bed salvage radiotherapy (SRT) if negative or positive within prostate bed, stereotactic body radiotherapy (SBRT) if pelvic nodal recurrences or oligometastatic disease, androgen deprivation therapy (ADT) if nonoligometastatic disease. Chi-square test was used to evaluate the relationship between baseline features and rate of positive PSMA PET/CT. RESULTS: One hundred patients were enrolled. PSMA results were negative/positive in the prostate bed in 72 patients, pelvic nodal or extrapelvic metastatic disease were detected in 23 and 5 patients. Twenty-one patients underwent observation because of prior postoperative radiotherapy (RT)/treatment refusal. Fifty patients were treated with prostate bed SRT, 23 patients underwent SBRT to pelvic nodal disease, five patients were treated with SBRT to oligometastatic disease. One patient underwent ADT. NCCN high-risk features, stage > pT3 and ISUP score >3 reported a significantly higher rate of positive PSMA PET/CT after restaging (p = 0.01, p = 0.02, and p = 0.002). By quartiles of PSA, rate of positive PSMA PET/CT was 26.9% (>0.2; <0.29 ng/mL), 24% (>0.3; <0.37 ng/mL), 26.9% (>0.38; <0.51 ng/mL), and 34.7% (>0. 52; <0.98 ng/mL). CONCLUSIONS: PSICHE trial constitute a useful platform to collect data within a clinical framework where modern imaging and metastasis-directed therapy are integrated.

The complementary role of PSMA expression and [18F]FDG PET/CT in predicting thyroid cancer outcome: from black and white to shades of gray, in the era of precision oncology.

BACKGROUND: The value of Prostate Specific Membrane Antigen (PSMA) in thyroid carcinoma (TC) is still unknown. We aimed to test the potential complementary role of PSMA expression and 2-[18F]fluoro-2-deoxy-D-glucose ([18F]FDG) uptake on PET/CT as biomarkers for TC outcome prediction. MATERIALS AND METHODS: From a retrospective cohort of TC patients we selected those fulfilling the following inclusion/exclusion criteria: thyroidectomy in our Institution, available primary tumor tissue PSMA immunostaining, [18F]FDG PET/CT and follow-up data. PSMA staining was visually assessed. PET/CT was considered positive in case of [18F]FDG uptake higher than the background at the site of TC confirmed by cyto-/histology, and/or follow-up. Disease recurrence, radioiodine refractoriness (RAI-R) and status at last follow-up (LFU) were used as outcome endpoints. RESULTS: We included 23 subjects. Disease recurrence occurred in 18 patients (median time 11 months, range 1-40); among these 12/18 developed RAI-R (median time 28 months, range 2-221), and 13/18 had evidence of disease at LFU. PSMA expression was negative in 6/23 cases. PET/CT was negative in 11/23 patients (7/11 experienced recurrence). PET/CT was positive in 9/12 patients showing RAI-R and 10/13 cases with evidence of disease at LFU. All patients with positive PET/CT had a positive PSMA immunostaining. Six out of 11 patients with negative PET/CT were positive at immunostaining, showing lower PSMA expression (median score of 30%, range 0-80%) than patients with positive PET/CT. The TC samples without PSMA expression belonged to patients who resulted negative also at PET/CT (3 experienced recurrence, 2 were RAI-R, and 1 had disease at LFU). Four out of 11 patients who resulted negative at PET/CT exhibited very high PSMA expression (≥ 70%) and although 3 of them experienced recurrence, none resulted RAI-R, and only 1 had persistent disease at LFU. CONCLUSIONS: Primary tumor PSMA expression and [18F]FDG uptake seem to play a complementary prognostic role in TC. The majority of patients who expressed PSMA recurred. In the intermediate ATA risk class, patients with negative PSMA immunostaining recurred less than patients expressing PSMA. Additionally, although patients with a negative [18F]FDG PET/CT had a favourable long-term outcome, PSMA assessment might be useful to timely identify subjects at higher risk of recurrence.

FAP expression in alpha cells of Langherhans insulae-implications for FAPI radiopharmaceuticals' use.

PURPOSE: Radiopharmaceuticals targeting fibroblast activation protein (FAP) alpha are increasingly studied for diagnostic and therapeutic applications. We discovered FAP expression at immunohistochemistry (IHC) in the alpha cells of the Langerhans insulae of few patients. Therefore, we planned an investigation aimed at describing FAP expression in the pancreas and discussing the implications for radioligand applications. METHODS: We retrospectively included 40 patients from 2 institutions (20 pts each) according to the following inclusion/exclusion criteria: (i) pathology proven pancreatic ductal adenocarcinoma and neuroendocrine tumors (NET), 10 pts per each group at each center; (ii) and availability of paraffin-embedded tissue; and (iii) clinical-pathological records. We performed IHC analysis and applied a semiquantitative visual scoring system (0, negative staining; 1, present in less than 30%; 2, present in more than 30% of the area). FAP expression was assessed according to histology-NET (n = 20) vs ductal adenocarcinoma (n = 20)-and to previous treatments within the adenocarcinoma group. The local ethics committee approved the study (No. INT 21/16, 28 January 2016). RESULTS: The population consisted of 24 males and 16 females, with a median age of 68 and a range of 14-84 years; 8/20 adenocarcinoma patients received chemotherapy. In all the Langerhans insulae (40/40), pancreatic alpha cells were found to express FAP, with a score of 2. No difference was found among NET (20/20) and adenocarcinoma (20/20), nor according to neoadjuvant chemotherapy in the adenocarcinoma cohort (received or not received). CONCLUSION: Pancreatic Langerhans islet alpha cells normally express FAP. This is not expected to influence the diagnostic accuracy of FAP-targeting tracers. In the therapeutic setting, our results suggest the need to better elucidate FAPI radioligands' effects on the Langerhans insulae function.

Early biochemical outcomes following PSMA guided approach for bIoCHEmical relapse after prostatectomy-PSICHE trial (NCT05022914): preliminary results.

PSICHE (NCT05022914) is a prospective trial to test a [68Ga]Ga- PSMA-11 PET/CT imaging tailored strategy. All evaluable patients had biochemical relapse after surgery and underwent centralized [68Ga]Ga-PSMA-11 PET/CT imaging. The treatment was performed according pre-defined criteria. Observation and re-staging at further PSA progression were proposed to patients with negative PSMA and previous postoperative RT. Prostate bed SRT was proposed to all patients with a negative staging or positive imaging within prostate bed. Stereotactic body radiotherapy (SBRT) to all sites of disease was used for all patients with pelvic nodal recurrence (nodal disease < 2 cm under aortic bifurcation) or oligometastatic disease. At 3 months after treatment, 54.7% of patients had a complete biochemical response Only 2 patients experienced G2 Genitourinary toxicity. No G2 Gastrointestinal toxicity was recorded. A PSMA targeted treatment strategy led to encouraging results and was well tolerated.

A virtual biopsy of liver parenchyma to predict the outcome of liver resection.

The preoperative risk assessment of liver resections (LR) is still an open issue. Liver parenchyma characteristics influence the outcome but cannot be adequately evaluated in the preoperative setting. The present study aims to elucidate the contribution of the radiomic analysis of non-tumoral parenchyma to the prediction of complications after elective LR. All consecutive patients undergoing LR between 2017 and 2021 having a preoperative computed tomography (CT) were included. Patients with associated biliary/colorectal resection were excluded. Radiomic features were extracted from a virtual biopsy of non-tumoral liver parenchyma (a 2 mL cylinder) outlined in the portal phase of preoperative CT. Data were internally validated. Overall, 378 patients were analyzed (245 males/133 females-median age 67 years-39 cirrhotics). Radiomics increased the performances of the preoperative clinical models for both liver dysfunction (at internal validaton, AUC = 0.727 vs. 0.678) and bile leak (AUC = 0.744 vs. 0.614). The final predictive model combined clinical and radiomic variables: for bile leak, segment 1 resection, exposure of Glissonean pedicles, HU-related indices, NGLDM_Contrast, GLRLM indices, and GLZLM_ZLNU; for liver dysfunction, cirrhosis, liver function tests, major hepatectomy, segment 1 resection, and NGLDM_Contrast. The combined clinical-radiomic model for bile leak based on preoperative data performed even better than the model including the intraoperative data (AUC = 0.629). The textural features extracted from a virtual biopsy of non-tumoral liver parenchyma improved the prediction of postoperative liver dysfunction and bile leak, implementing information given by standard clinical data. Radiomics should become part of the preoperative assessment of candidates to LR.

Explainable domain transfer of distant supervised cancer subtyping model via imaging-based rules extraction.

Image texture analysis has for decades represented a promising opportunity for cancer assessment and disease progression evaluation, evolving in a discipline, i.e., radiomics. However, the road to a complete translation into clinical practice is still hampered by intrinsic limitations. As purely supervised classification models fail in devising robust imaging-based biomarkers for prognosis, cancer subtyping approaches would benefit from the employment of distant supervision, for instance exploiting survival/recurrence information. In this work, we assessed, tested, and validated the domain-generality of our previously proposed Distant Supervised Cancer Subtyping model on Hodgkin Lymphoma. We evaluate the model performance on two independent datasets coming from two hospitals, comparing and analyzing the results. Although successful and consistent, the comparison confirmed the instability of radiomics due to an across-center lack of reproducibility, leading to explainable results in one center and poor interpretability in the other. We thus propose a Random Forest-based Explainable Transfer Model for testing the domain-invariance of imaging biomarkers extracted from retrospective cancer subtyping. In doing so, we tested the predictive ability of cancer subtyping in a validation and perspective setting, which led to successful results and supported the domain-generality of the proposed approach. On the other hand, the extraction of decision rules enables to draw of risk factors and robust biomarkers to inform clinical decisions. This work shows the potentialities of the Distant Supervised Cancer Subtyping model to be further evaluated in larger multi-center datasets, to reliably translate radiomics into medical practice. The code is available at this GitHub repository.

Mapping Tumor Heterogeneity via Local Entropy Assessment: Making Biomarkers Visible.

Advanced imaging and analysis improve prediction of pathology data and outcomes in several tumors, with entropy-based measures being among the most promising biomarkers. However, entropy is often perceived as statistical data lacking clinical significance. We aimed to generate a voxel-by-voxel visual map of local tumor entropy, thus allowing to (1) make entropy explainable and accessible to clinicians; (2) disclose and quantitively characterize any intra-tumoral entropy heterogeneity; (3) evaluate associations between entropy and pathology data. We analyzed the portal phase of preoperative CT of 20 patients undergoing liver surgery for colorectal metastases. A three-dimensional core kernel (5 × 5 × 5 voxels) was created and used to compute the local entropy value for each voxel of the tumor. The map was encoded with a color palette. We performed two analyses: (a) qualitative assessment of tumors' detectability and pattern of entropy distribution; (b) quantitative analysis of the entropy values distribution. The latter data were compared with standard Hounsfield data as predictors of post-chemotherapy tumor regression grade (TRG). Entropy maps were successfully built for all tumors. Metastases were qualitatively hyper-entropic compared to surrounding parenchyma. In four cases hyper-entropic areas exceeded the tumor margin visible at CT. We identified four "entropic" patterns: homogeneous, inhomogeneous, peripheral rim, and mixed. At quantitative analysis, entropy-derived data (percentiles/mean/median/root mean square) predicted TRG (p < 0.05) better than Hounsfield-derived ones (p = n.s.). We present a standardized imaging technique to visualize tumor heterogeneity built on a voxel-by-voxel entropy assessment. The association of local entropy with pathology data supports its role as a biomarker.

Radiomics-Based Inter-Lesion Relation Network to Describe [18F]FMCH PET/CT Imaging Phenotypes in Prostate Cancer.

Advanced image analysis, including radiomics, has recently acquired recognition as a source of biomarkers, although there are some technical and methodological challenges to face for its application in the clinic. Among others, proper phenotyping of metastatic or systemic disease where multiple lesions coexist is an issue, since each lesion contributes to characterization of the disease. Therefore, the radiomic profile of each lesion should be modeled into a more complex architecture able to reproduce each "unit" (lesion) as a part of the "entire" (patient). This work aimed to characterize intra-tumor heterogeneity underpinning metastatic prostate cancer using an exhaustive innovative approach which consist of a i) feature transformation method to build an agnostic (i.e., irrespective of pre-existence knowledge, experience, and expertise) radiomic profile of lesions extracted from [18F]FMCH PET/CT, ii) qualitative assessment of intra-tumor heterogeneity of patients, iii) quantitative representation of the intra-tumor heterogeneity of patients in terms of the relationship between their lesions' profiles, to be associated with prognostic factors. We confirmed that metastatic prostate cancer patients encompassed lesions with different radiomic profiles that exhibited intra-tumor radiomic heterogeneity and that the presence of many radiomic profiles within the same patient impacted the outcome.