Prognostic relevance of sarcopenia, geriatric, and nutritional assessments in older patients with diffuse large B-cell lymphoma: results of a multicentric prospective cohort study.

This prospective study aimed to investigate the prognostic effect of sarcopenia, geriatric, and nutritional status in older patients with diffuse large B-cell lymphoma (DLBCL). Ninety-five patients with DLBCL older than 70 years who were treated with immunochemotherapy were included. The lumbar L3 skeletal muscle index (L3-SMI) was measured by computed tomography at baseline, and sarcopenia was defined as low L3-SMI. Geriatric assessment included G8 score, CIRS-G scale, Timed Up and Go test, and instrumental activity of daily living. Nutritional status was assessed using the Mini Nutritional Assessment and the body mass index, and several scores used in the literature incorporating nutritional and inflammatory biomarkers, namely the Nutritional and inflammatory status (NIS), Geriatric Nutritional Risk Index, Prognostic Nutritional Index, and Glasgow Prognostic Score.Fifty-three patients were considered sarcopenic. Sarcopenic patients displayed higher levels of inflammation markers and lower levels of prealbumin than non-sarcopenic patients. Sarcopenia was associated with NIS, but was not associated with severe adverse events and treatment disruptions. They were, however, more frequent among patients with elevated NIS. Sarcopenia did not appear in this study as a prognostic factor for progression-free survival (PFS) or overall survival (OS). However, NIS emerged as predictive of the outcome with a 2-year PFS rate of 88% in the NIS ≤ 1 group and 49% in the NIS > 1 group and a significant effect in a multivariate analysis for both PFS (p = 0.049) and OS (HR = 9.61, CI 95% = [1.03-89.66], p = 0.04). Sarcopenia was not associated with adverse outcomes, but was related to NIS, which appeared to be an independent prognostic factor.

Deep learning analysis of contrast-enhanced spectral mammography to determine histoprognostic factors of malignant breast tumours.

OBJECTIVE: To evaluate if a deep learning model can be used to characterise breast cancers on contrast-enhanced spectral mammography (CESM). METHODS: This retrospective mono-centric study included biopsy-proven invasive cancers with an enhancement on CESM. CESM images include low-energy images (LE) comparable to digital mammography and dual-energy subtracted images (DES) showing tumour angiogenesis. For each lesion, histologic type, tumour grade, estrogen receptor (ER) status, progesterone receptor (PR) status, HER-2 status, Ki-67 proliferation index, and the size of the invasive tumour were retrieved. The deep learning model used was a CheXNet-based model fine-tuned on CESM dataset. The area under the curve (AUC) of the receiver operating characteristic (ROC) curve was calculated for the different models: images by images and then by majority voting combining all the incidences for one tumour. RESULTS: In total, 447 invasive breast cancers detected on CESM with pathological evidence, in 389 patients, which represented 2460 images analysed, were included. Concerning the ER, the deep learning model on the DES images had an AUC of 0.83 with the image-by-image analysis and of 0.85 for the majority voting. For the triple-negative analysis, a high AUC was observable for all models, in particularity for the model on LE images with an AUC of 0.90 for the image-by-image analysis and 0.91 for the majority voting. The AUC for the other histoprognostic factors was lower. CONCLUSION: Deep learning analysis on CESM has the potential to determine histoprognostic tumours makers, notably estrogen receptor status, and triple-negative receptor status. KEY POINTS: • A deep learning model developed for chest radiography was adapted by fine-tuning to be used on contrast-enhanced spectral mammography. • The adapted models allowed to determine for invasive breast cancers the status of estrogen receptors and triple-negative receptors. • Such models applied to contrast-enhanced spectral mammography could provide rapid prognostic and predictive information.

Correction: Brochet et al. A Quantitative Comparison between Shannon and Tsallis-Havrda-Charvat Entropies Applied to Cancer Outcome Prediction. Entropy 2022, 24, 436.

Alexandre Huat, Sébastien Thureau, David Pasquier, Isabelle Gardin, Romain Modzelewski, David Gibon, Juliette Thariat and Vincent Grégoire were not included as authors in the original publication [...].

A Quantitative Comparison between Shannon and Tsallis-Havrda-Charvat Entropies Applied to Cancer Outcome Prediction.

In this paper, we propose to quantitatively compare loss functions based on parameterized Tsallis-Havrda-Charvat entropy and classical Shannon entropy for the training of a deep network in the case of small datasets which are usually encountered in medical applications. Shannon cross-entropy is widely used as a loss function for most neural networks applied to the segmentation, classification and detection of images. Shannon entropy is a particular case of Tsallis-Havrda-Charvat entropy. In this work, we compare these two entropies through a medical application for predicting recurrence in patients with head-neck and lung cancers after treatment. Based on both CT images and patient information, a multitask deep neural network is proposed to perform a recurrence prediction task using cross-entropy as a loss function and an image reconstruction task. Tsallis-Havrda-Charvat cross-entropy is a parameterized cross-entropy with the parameter α. Shannon entropy is a particular case of Tsallis-Havrda-Charvat entropy for α=1. The influence of this parameter on the final prediction results is studied. In this paper, the experiments are conducted on two datasets including in total 580 patients, of whom 434 suffered from head-neck cancers and 146 from lung cancers. The results show that Tsallis-Havrda-Charvat entropy can achieve better performance in terms of prediction accuracy with some values of α.

Radiotherapy boost in patients with hypoxic lesions identified by 18F-FMISO PET/CT in non-small-cell lung carcinoma: can we expect a better survival outcome without toxicity? [RTEP5 long-term follow-up].

PURPOSE: Chemoradiotherapy is the reference curative-intent treatment for nonresectable locally advanced non-small-cell lung carcinoma (NSCLC), with unsatisfactory survival, partially due to radiation resistance in hypoxic tissues. The objective was to update survival and toxicity at 3 years following radiotherapy boost to hypoxic tumours in NSCLC patients treated with curative-intent chemoradiotherapy. METHODS: This was an open-label, nonrandomized, multicentre, phase II clinical trial. 18F-Fluoromisonidazole (18F-FMISO) PET/CT was used to determine the hypoxic profile of the patients. 18F-FMISO-positive patients and those without organ-at-risk constraints received a radiotherapy boost (70-84 Gy); the others received standard radiotherapy (66 Gy). Overall survival (OS), progression-free survival (PFS) and safety were assessed. RESULTS: A total of 54 patients were evaluated. OS and PFS rates at 3 years were 48.5% and 28.8%, respectively. The median OS in the 18F-FMISO-positive patients was 25.8 months and was not reached in the 18F-FMISO-negative patients (p = 0.01). A difference between the groups was also observed for PFS (12 months vs. 26.2 months, p = 0.048). In 18F-FMISO-positive patients, no difference was observed in OS in relation to dose, probably because of the small sample size (p = 0.30). However, the median OS seemed to be in favour of patients who received the radiotherapy boost (26.5 vs. 15.3 months, p = 0.71). In patients who received the radiotherapy boost, no significant late toxicities were observed. CONCLUSION: 18F-FMISO uptake in NSCLC patients is strongly associated with features indicating a poor prognosis. In 18F-FMISO-positive patients, the radiotherapy boost seemed to improve the OS by 11.2 months. A further clinical trial is needed to investigate the efficacy of a radiotherapy boost in patients with hypoxic tumours.

High FDG uptake areas on pre-radiotherapy PET/CT identify preferential sites of local relapse after chemoradiotherapy for locally advanced oesophageal cancer.

PURPOSE: The high failure rates in the radiotherapy (RT) target volume suggest that patients with locally advanced oesophageal cancer (LAOC) would benefit from increased total RT doses. High 2-deoxy-2-[(18)F]fluoro-D-glucose (FDG) uptake (hotspot) on pre-RT FDG positron emission tomography (PET)/CT has been reported to identify intra-tumour sites at increased risk of relapse after RT in non-small cell lung cancer and in rectal cancer. Our aim was to confirm these observations in patients with LAOC and to determine the optimal maximum standardized uptake value (SUVmax) threshold to delineate smaller RT target volumes that would facilitate RT dose escalation without impaired tolerance. METHODS: The study included 98 consecutive patients with LAOC treated by chemoradiotherapy (CRT). All patients underwent FDG PET/CT at initial staging and during systematic follow-up in a single institution. FDG PET/CT acquisitions were coregistered on the initial CT scan. Various subvolumes within the initial tumour (30, 40, 50, 60, 70, 80 and 90% SUVmax thresholds) and in the subsequent local recurrence (LR, 40 and 90% SUVmax thresholds) were pasted on the initial CT scan and compared[Dice, Jaccard, overlap fraction (OF), common volume/baseline volume, common volume/recurrent volume]. RESULTS: Thirty-five patients had LR. The initial metabolic tumour volume was significantly higher in LR tumours than in the locally controlled tumours (mean 25.4 vs 14.2 cc; p = 0.002). The subvolumes delineated on initial PET/CT with a 30-60% SUVmax threshold were in good agreement with the recurrent volume at 40% SUVmax (OF = 0.60-0.80). The subvolumes delineated on initial PET/CT with a 30-60% SUVmax threshold were in good to excellent agreement with the core volume (90% SUVmax) of the relapse (common volume/recurrent volume and OF indices 0.61-0.89). CONCLUSION: High FDG uptake on pretreatment PET/CT identifies tumour subvolumes that are at greater risk of recurrence after CRT in patients with LAOC. We propose a 60% SUVmax threshold to delineate high FDG uptake areas on initial PET/CT as reduced target volumes for RT dose escalation.

Pretreatment metabolic tumour volume is predictive of disease-free survival and overall survival in patients with oesophageal squamous cell carcinoma.

PURPOSE: It has been suggested that FDG PET has predictive value for the prognosis of treated oesophageal carcinoma. However, the studies reported in the literature have shown discordant results. The aim of this study was to determine whether pretherapy quantitative metabolic parameters correlate with patient outcomes. METHODS: Included in the study were 67 patients with a histological diagnosis of oesophageal squamous cell carcinoma. Each patient underwent (18)F-FDG PET (4.5 MBq/kg) before chemoradiotherapy. Quantitative analysis was performed using the following parameters: age, weight loss, location, N stage, OMS performance status, MTVp and MTVp' (metabolic tumour volume determined by two different physicians), MTV40% (volume for a threshold of 40 % of SUVmax), MTVa (volume automatically determined with a contrast-based adaptive threshold method), SUVmax, SUVmean and TLG (total lesion glycolysis). RESULTS: MTVp and MTV40% were highly correlated (Pearson's index 0.92). SUVmeanp and SUVmean40% were also correlated (Pearson's index 0.86), as were TLGp and TLG40% (Pearson's index 0.98). Similarly, the parameters obtained with the adaptive threshold method (MTVa, SUVmeana and TLGa) were correlated with those obtained manually (MTVp, SUVmeanp and TLGp). The manual metabolic tumour volume determination (MTVp and MTVp') was reproducible. Multivariate analysis for disease-free survival (DFS) showed that a larger MTVp was associated with a shorter DFS (p = 0.004) and that a higher SUVmax was associated with a longer DFS (p = 0.02). Multivariate analysis for overall survival (OS) showed that a larger MTVp was associated with a shorter OS (p = 0.01) and that a tumour in the distal oesophagus was associated with a longer OS (p = 0.005). The associations among the other parameters were not statistically significant. CONCLUSION: Metabolic tumour volume is a major prognostic factor for DFS and OS in patients with oesophageal squamous cell carcinoma. Higher SUVmax values were paradoxically associated with longer survival. The location of the tumour also appeared to affect prognosis.

FDG PET during radiochemotherapy is predictive of outcome at 1 year in non-small-cell lung cancer patients: a prospective multicentre study (RTEP2).

PURPOSE: To assess prospectively the prognostic value of FDG PET/CT during curative-intent radiotherapy (RT) with or without concomitant chemotherapy in patients with non-small-cell lung cancer (NSCLC). METHODS: Patients with histological proof of invasive localized NSCLC and evaluable tumour, and who were candidates for curative-intent radiochemotherapy (RCT) or RT were preincluded after providing written informed consent. Definitive inclusion was conditional upon significant FDG uptake before RT (PET1). All included patients had a FDG PET/CT scan during RT (PET2, mean dose 43 Gy) and were evaluated by FDG PET/CT at 3 months and 1 year after RT. The main endpoint was death (from whatever cause) or tumour progression at 1 year. RESULTS: Of 77 patients preincluded, 52 were evaluable. Among the evaluable patients, 77% received RT with induction chemotherapy and 73% RT with concomitant chemotherapy. At 1 year, 40 patients (77 %) had died or had tumour progression. No statistically significant association was found between stage (IIIB vs. other), histology (squamous cell carcinoma vs. other), induction or concomitant chemotherapy, and death/tumour progression at 1 year. The SUVmax in the PET2 scan was the single variable predictive of death or tumour progression at 1 year (odds ratio 1.97, 95% CI 1.25 - 3.09, p = 0.003) in multivariate analysis. The area under the receiver operating characteristic curve was 0.85 (95% CI 0.73 - 0.94, p < 10(-4)). A SUVmax value of 5.3 in the PET2 scan yielded a sensitivity of 70% and a specificity of 92% for predicting tumour progression or death at 1 year. CONCLUSION: This prospective multicentre study demonstrated the prognostic value in terms of disease-free survival of SUVmax assessed during the 5th week of curative-intent RT or RCT in NSCLC patients (NCT01261598; RTEP2 study).

Prognostic impact of fat tissue loss and cachexia assessed by computed tomography scan in elderly patients with diffuse large B-cell lymphoma treated with immunochemotherapy.

OBJECTIVES: Approximately 30% of DLBCL patients are older than 70 yr. This study evaluated the prognostic impact of a cachexia score (CS) including fat tissue loss (adipopenia) and sarcopenia as assessed by computed tomography (CT scan) in elderly DLBCL patients treated with chemotherapy and rituximab (R). METHODS: This retrospective analysis included 80 DLBCL patients older than 70 yr treated with R-CHOP or R-miniCHOP. Skeletal muscle (SM) and visceral (V) and subcutaneous (S) adipose (A) tissues were measured by analysing CT images at the third lumbar (L3) level. RESULTS: The median age of the patients was 78 yr. Forty-four and 46 patients were considered sarcopenic and adipopenic, respectively. The median progression-free survival (PFS) was 13.6 months in the adipopenic group and 49.4 months in the non-adipopenic group [hazard ratio (HR) = 2.27; 95% confidence interval (CI): 1.3-4; P = 0.0042]. The median overall survival (OS) was 25.7 months in the adipopenic group and 57.1 months in the non-adipopenic group (HR = 1.93; 95% CI: 1.05-3.55; P = 0.0342). A two-point CS including adipopenia and sarcopenia was created and defined two distinct risk groups with differences in outcomes that were highly significant. The CS was predictive of the prognosis in a multivariate analysis including body mass index (BMI) (< or ≥ 25 kg/m(2) ), age (< or ≥ 80 yr), international prognostic index (IPI) and albuminaemia (HR = 3.67; 95% CI = 1.93-6.97; P < 0.0001). CONCLUSION: A CS including sarcopenia and adipopenia, assessed by a single CT scan slice, predicts outcome independent of BMI and the IPI.

Assessing Interobserver Variability in the Delineation of Structures in Radiation Oncology: A Systematic Review.

PURPOSE: The delineation of target volumes and organs at risk is the main source of uncertainty in radiation therapy. Numerous interobserver variability (IOV) studies have been conducted, often with unclear methodology and nonstandardized reporting. We aimed to identify the parameters chosen in conducting delineation IOV studies and assess their performances and limits. METHODS AND MATERIALS: We conducted a systematic literature review to highlight major points of heterogeneity and missing data in IOV studies published between 2018 and 2021. For the main used metrics, we did in silico analyses to assess their limits in specific clinical situations. RESULTS: All disease sites were represented in the 66 studies examined. Organs at risk were studied independently of tumor site in 29% of reviewed IOV studies. In 65% of studies, statistical analyses were performed. No gold standard (GS; ie, reference) was defined in 36% of studies. A single expert was considered as the GS in 21% of studies, without testing intraobserver variability. All studies reported both absolute and relative indices, including the Dice similarity coefficient (DSC) in 68% and the Hausdorff distance (HD) in 42%. Limitations were shown in silico for small structures when using the DSC and dependence on irregular shapes when using the HD. Variations in DSC values were large between studies, and their thresholds were inconsistent. Most studies (51%) included 1 to 10 cases. The median number of observers or experts was 7 (range, 2-35). The intraclass correlation coefficient was reported in only 9% of cases. Investigating the feasibility of studying IOV in delineation, a minimum of 8 observers with 3 cases, or 11 observers with 2 cases, was required to demonstrate moderate reproducibility. CONCLUSIONS: Implementation of future IOV studies would benefit from a more standardized methodology: clear definitions of the gold standard and metrics and a justification of the tradeoffs made in the choice of the number of observers and number of delineated cases should be provided.

Prediction of brain tumor recurrence location based on multi-modal fusion and nonlinear correlation learning.

Brain tumor is one of the leading causes of cancer death. The high-grade brain tumors are easier to recurrent even after standard treatment. Therefore, developing a method to predict brain tumor recurrence location plays an important role in the treatment planning and it can potentially prolong patient's survival time. There is still little work to deal with this issue. In this paper, we present a deep learning-based brain tumor recurrence location prediction network. Since the dataset is usually small, we propose to use transfer learning to improve the prediction. We first train a multi-modal brain tumor segmentation network on the public dataset BraTS 2021. Then, the pre-trained encoder is transferred to our private dataset for extracting the rich semantic features. Following that, a multi-scale multi-channel feature fusion model and a nonlinear correlation learning module are developed to learn the effective features. The correlation between multi-channel features is modeled by a nonlinear equation. To measure the similarity between the distributions of original features of one modality and the estimated correlated features of another modality, we propose to use Kullback-Leibler divergence. Based on this divergence, a correlation loss function is designed to maximize the similarity between the two feature distributions. Finally, two decoders are constructed to jointly segment the present brain tumor and predict its future tumor recurrence location. To the best of our knowledge, this is the first work that can segment the present tumor and at the same time predict future tumor recurrence location, making the treatment planning more efficient and precise. The experimental results demonstrated the effectiveness of our proposed method to predict the brain tumor recurrence location from the limited dataset.

Evaluation of sarcopenia biomarkers in older patients undergoing major surgery for digestive cancer. SAXO prospective cohort study.

BACKGROUND: The aim of the study was to prospectively evaluate different biomarkers to identify the most reliable for anticipating complications after major abdominal surgery for digestive cancer in older patients and compare their performance to the existing definition and screening algorithm of sarcopenia from EWGSOP. METHODS: Ninety-five consecutive patients aged over 65 years who underwent elective surgery for digestive cancer were prospectively included in the SAXO study. Sarcopenia was defined according to EWGSOP criteria (four level from no sarcopenia to severe sarcopenia). Strength and physical performance were evaluated with the handgrip test (HGT) and gait speed test (GST), respectively. CT scan analysis was used to calculate the skeletal muscle index (SMI), intermuscular adipose tissue (IMAT), visceral adipose tissue (VAT), and subcutaneous adipose tissue (SAT). Measures were adjusted to body mass index (BMI). Complication grading was performed using the Clavien‒Dindo classification. A doubly robust estimator with multivariable regression was used to limit bias. RESULTS: Sixteen patients presented with sarcopenia. Adjusted to BMI, sarcopenic patients had an increased IMATBMI (0.35 vs. 0.22; p = 0.003) and increased VATBMI (7.85 vs. 6.13; p = 0.048). In multivariable analysis, IMAT was an independent risk factor for minor and severe complications (OR = 1.298; 95% CI [1.031: 1.635] p = 0.027), while an increased SAT area was a protective factor (OR = 0.982; 95% CI [0.969: 0.995] p = 0.007). Twenty-two patients were obese (BMI ≥30 kg/m2). While no association was observed between obesity and sarcopenia (according to EWGSOP definition), obese patients had increased IMATBMI (0.31 vs. 0.23; p = 0.010) and VATBMI (8.40 vs. 6.49; p = 0.019). The combination of SAT, VAT and IMAT performed well to anticipate severe complication (AUC = 0.759) while AUC of EWGSOP 2010 and 2019 algorithm were 0.660 and 0.519, respectively. DISCUSSION: Non-invasive and imaging related measures of IMAT, SAT and VAT seems to be valuable tools to refine risk-assessment of older patients in surgery and specially to detect myosteatosis in obese ones.

Quantitative MRI to Characterize Hypoxic Tumors in Comparison to FMISO PET/CT for Radiotherapy in Oropharynx Cancers.

Intratumoral hypoxia is associated with a poor prognosis and poor response to treatment in head and neck cancers. Its identification would allow for increasing the radiation dose to hypoxic tumor subvolumes. 18F-FMISO PET imaging is the gold standard; however, quantitative multiparametric MRI could show the presence of intratumoral hypoxia. Thus, 16 patients were prospectively included and underwent 18F-FDG PET/CT, 18F-FMISO PET/CT, and multiparametric quantitative MRI (DCE, diffusion and relaxometry T1 and T2 techniques) in the same position before treatment. PET and MRI sub-volumes were segmented and classified as hypoxic or non-hypoxic volumes to compare quantitative MRI parameters between normoxic and hypoxic volumes. In total, 13 patients had hypoxic lesions. The Dice, Jaccard, and overlap fraction similarity indices were 0.43, 0.28, and 0.71, respectively, between the FDG PET and MRI-measured lesion volumes, showing that the FDG PET tumor volume is partially contained within the MRI tumor volume. The results showed significant differences in the parameters of SUV in FDG and FMISO PET between patients with and without measurable hypoxic lesions. The quantitative MRI parameters of ADC, T1 max mapping and T2 max mapping were different between hypoxic and normoxic subvolumes. Quantitative MRI, based on free water diffusion and T1 and T2 mapping, seems to be able to identify intra-tumoral hypoxic sub-volumes for additional radiotherapy doses.

High prevalence of pre-existing sarcopenia in critically ill patients with hematologic malignancies admitted to the intensive care unit for sepsis or septic shock.

BACKGROUND & AIMS: We aimed to evaluate body composition (BC) by computed tomography (CT) in hematologic malignancy (HM) patients admitted to the intensive care unit (ICU) for sepsis or septic shock. METHODS: We retrospectively assessed BC and its impact on outcome of 186 patients at the 3rd lumbar (L3) and 12th thoracic vertebral levels (T12) using CT-scan performed before ICU admission. RESULTS: The median patient age was 58.0 [47; 69] years. Patients displayed adverse clinical characteristics at admission with median [q1; q3] SAPS II and SOFA scores of 52 [40; 66] and 8 [5; 12], respectively. The mortality rate in the ICU was 45.7%. Overall survival rates at 1 month after admission in the pre-existing sarcopenic vs. non pre-existing sarcopenic patients were 47.9% (95% CI [37.6; 61.0]) and 55.0% (95% CI [41.6; 72.8]), p = 0.99), respectively, at the L3 level and 48.4% (95% CI [40.4; 58.0]) vs. 66.7% (95% CI [51.1; 87.0]), p = 0.062), respectively, at the T12 level. CONCLUSIONS: Sarcopenia is assessable by CT scan at both the T12 and L3 levels and is highly prevalent in HM patients admitted to the ICU for severe infections. Sarcopenia may contribute to the high mortality rate in the ICU in this population.

Weakly Supervised Tumor Detection in PET Using Class Response for Treatment Outcome Prediction.

It is proven that radiomic characteristics extracted from the tumor region are predictive. The first step in radiomic analysis is the segmentation of the lesion. However, this task is time consuming and requires a highly trained physician. This process could be automated using computer-aided detection (CAD) tools. Current state-of-the-art methods are trained in a supervised learning setting, which requires a lot of data that are usually not available in the medical imaging field. The challenge is to train one model to segment different types of tumors with only a weak segmentation ground truth. In this work, we propose a prediction framework including a 3D tumor segmentation in positron emission tomography (PET) images, based on a weakly supervised deep learning method, and an outcome prediction based on a 3D-CNN classifier applied to the segmented tumor regions. The key step is to locate the tumor in 3D. We propose to (1) calculate two maximum intensity projection (MIP) images from 3D PET images in two directions, (2) classify the MIP images into different types of cancers, (3) generate the class activation maps through a multitask learning approach with a weak prior knowledge, and (4) segment the 3D tumor region from the two 2D activation maps with a proposed new loss function for the multitask. The proposed approach achieves state-of-the-art prediction results with a small data set and with a weak segmentation ground truth. Our model was tested and validated for treatment response and survival in lung and esophageal cancers on 195 patients, with an area under the receiver operating characteristic curve (AUC) of 67% and 59%, respectively, and a dice coefficient of 73% and 0.77% for tumor segmentation.

Multi-task multi-scale learning for outcome prediction in 3D PET images.

BACKGROUND AND OBJECTIVES: Predicting patient response to treatment and survival in oncology is a prominent way towards precision medicine. To this end, radiomics has been proposed as a field of study where images are used instead of invasive methods. The first step in radiomic analysis in oncology is lesion segmentation. However, this task is time consuming and can be physician subjective. Automated tools based on supervised deep learning have made great progress in helping physicians. However, they are data hungry, and annotated data remains a major issue in the medical field where only a small subset of annotated images are available. METHODS: In this work, we propose a multi-task, multi-scale learning framework to predict patient's survival and response. We show that the encoder can leverage multiple tasks to extract meaningful and powerful features that improve radiomic performance. We also show that subsidiary tasks serve as an inductive bias so that the model can better generalize. RESULTS: Our model was tested and validated for treatment response and survival in esophageal and lung cancers, with an area under the ROC curve of 77% and 71% respectively, outperforming single-task learning methods. CONCLUSIONS: Multi-task multi-scale learning enables higher performance of radiomic analysis by extracting rich information from intratumoral and peritumoral regions.

Clinical and phantom validation of a deep learning based denoising algorithm for F-18-FDG PET images from lower detection counting in comparison with the standard acquisition.

BACKGROUND: PET/CT image quality is directly influenced by the F-18-FDG injected activity. The higher the injected activity, the less noise in the reconstructed images but the more radioactive staff exposition. A new FDA cleared software has been introduced to obtain clinical PET images, acquired at 25% of the count statistics considering US practices. Our aim is to determine the limits of a deep learning based denoising algorithm (SubtlePET) applied to statistically reduced PET raw data from 3 different last generation PET scanners in comparison to the regular acquisition in phantom and patients, considering the European guidelines for radiotracer injection activities. Images of low and high contrasted (SBR = 2 and 5) spheres of the IEC phantom and high contrast (SBR = 5) of micro-spheres of Jaszczak phantom were acquired on 3 different PET devices. 110 patients with different pathologies were included. The data was acquired in list-mode and retrospectively reconstructed with the regular acquisition count statistic (PET100), 50% reduction in counts (PET50) and 66% reduction in counts (PET33). These count reduced images were post-processed with SubtlePET to obtain PET50 + SP and PET33 + SP images. Patient image quality was scored by 2 senior nuclear physicians. Peak-signal-to-Noise and Structural similarity metrics were computed to compare the low count images to regular acquisition (PET100). RESULTS: SubtlePET reliably denoised the images and maintained the SUVmax values in PET50 + SP. SubtlePET enhanced images (PET33 + SP) had slightly increased noise compared to PET100 and could lead to a potential loss of information in terms of lesion detectability. Regarding the patient datasets, the PET100 and PET50 + SP were qualitatively comparable. The SubtlePET algorithm was able to correctly recover the SUVmax values of the lesions and maintain a noise level equivalent to full-time images. CONCLUSION: Based on our results, SubtlePET is adapted in clinical practice for half-time or half-dose acquisitions based on European recommended injected dose of 3 MBq/kg without diagnostic confidence loss.

αvß3 imaging can accurately distinguish between mature teratoma and necrosis in 18F-FDG-negative residual masses after treatment of non-seminomatous testicular cancer: a preclinical study.

PURPOSE: We assessed whether imaging α(v)ß(3) integrin could distinguish mature teratoma from necrosis in human non-seminomatous germ cell tumour (NSGCT) post-chemotherapy residual masses. METHODS: Human embryonal carcinoma xenografts (six/rat) were untreated (controls) or treated to form mature teratomas with low-dose cisplatin and all-trans retinoic acid (ATRA) over a period of 8 weeks. In another group, necrosis was induced in xenografts with high-dose cisplatin plus etoposide (two cycles). (18)F-Fluorodeoxyglucose ((18)F-FDG) small animal positron emission tomography (SA PET) imaging was performed in three rats (one control and two treated for 4 and 8 weeks with cisplatin+ATRA). Imaging of α(v)ß(3) expression was performed in six rats bearing mature teratomas and two rats with necrotic lesions on a microSPECT/CT device after injection of the tracer [(99m)Tc]HYNIC-RGD [6-hydrazinonicotinic acid conjugated to cyclo(Arg-Gly-Asp-D-Phe-Lys)]. Correlative immunohistochemistry studies of human and mouse α(v)ß(3) expression were performed. RESULTS: Cisplatin+ATRA induced differentiation of the xenografts. After 8 weeks, some glandular structures and mesenchymal cells were visible; in contrast, control tumours showed undifferentiated tissues. SA PET imaging showed that mature teratoma had very low avidity for (18)F-FDG [mean standardised uptake value (SUV(mean)) = 0.48 ± 0.05] compared to untreated embryonal carcinoma (SUV(mean) = 0.92 ± 0.13) (p = 0.005). α(v)ß(3) imaging accurately distinguished mature teratoma (tumour to muscle ratio = 4.29 ± 1.57) from necrosis (tumour to muscle ratio = 1.3 ± 0.26) (p = 0.0002). Immunohistochemistry studies showed that α(v)ß(3) integrin expression was strong in the glandular structures of mature teratoma lesions and negative in host stroma. CONCLUSION: Imaging α(v)ß(3) integrin accurately distinguished mature teratoma from necrosis following cisplatin-based treatment in human NSGCT xenografts.

Evaluation of an Automatic Classification Algorithm Using Convolutional Neural Networks in Oncological Positron Emission Tomography.

Introduction: Our aim was to evaluate the performance in clinical research and in clinical routine of a research prototype, called positron emission tomography (PET) Assisted Reporting System (PARS) (Siemens Healthineers) and based on a convolutional neural network (CNN), which is designed to detect suspected cancer sites in fluorine-18 fluorodeoxyglucose (18F-FDG) PET/computed tomography (CT). Method: We retrospectively studied two cohorts of patients. The first cohort consisted of research-based patients who underwent PET scans as part of the initial workup for diffuse large B-cell lymphoma (DLBCL). The second cohort consisted of patients who underwent PET scans as part of the evaluation of miscellaneous cancers in clinical routine. In both cohorts, we assessed the correlation between manually and automatically segmented total metabolic tumor volumes (TMTVs), and the overlap between both segmentations (Dice score). For the research cohort, we also compared the prognostic value for progression-free survival (PFS) and overall survival (OS) of manually and automatically obtained TMTVs. Results: For the first cohort (research cohort), data from 119 patients were retrospectively analyzed. The median Dice score between automatic and manual segmentations was 0.65. The intraclass correlation coefficient between automatically and manually obtained TMTVs was 0.68. Both TMTV results were predictive of PFS (hazard ratio: 2.1 and 3.3 for automatically based and manually based TMTVs, respectively) and OS (hazard ratio: 2.4 and 3.1 for automatically based and manually based TMTVs, respectively). For the second cohort (routine cohort), data from 430 patients were retrospectively analyzed. The median Dice score between automatic and manual segmentations was 0.48. The intraclass correlation coefficient between automatically and manually obtained TMTVs was 0.61. Conclusion: The TMTVs determined for the research cohort remain predictive of total and PFS for DLBCL. However, the segmentations and TMTVs determined automatically by the algorithm need to be verified and, sometimes, corrected to be similar to the manual segmentation.