An unusual case of primary splenic soft part alveolar sarcoma: case report and review of the literature with emphasis on the spectrum of TFE3-associated neoplasms.

BACKGROUND: Alveolar soft part sarcoma is a rare tumour of soft tissues, mostly localized in muscles or deep soft tissues of the extremities. In rare occasions, this tumour develops in deep tissues of the abdomen or pelvis. CASE PRESENTATION: In this case report, we described the case of a 46 year old man who developed a primary splenic alveolar soft part sarcoma. The tumour displayed typical morphological alveolar aspect, as well as immunohistochemical profile notably TFE3 nuclear staining. Detection of ASPSCR1 Exon 7::TFE3 Exon 6 fusion transcript in molecular biology and TFE3 rearrangement in FISH confirmed the diagnosis. CONCLUSION: We described the first case of primary splenic alveolar soft part sarcoma, which questions once again the cell of origin of this rare tumour.

Efficient brain tumor segmentation using Swin transformer and enhanced local self-attention.

PURPOSE: Fully convolutional neural networks architectures have proven to be useful for brain tumor segmentation tasks. However, their performance in learning long-range dependencies is limited to their localized receptive fields. On the other hand, vision transformers (ViTs), essentially based on a multi-head self-attention mechanism, which generates attention maps to aggregate spatial information dynamically, have outperformed convolutional neural networks (CNNs). Inspired by the recent success of ViT models for the medical images segmentation, we propose in this paper a new network based on Swin transformer for semantic brain tumor segmentation. METHODS: The proposed method for brain tumor segmentation combines Transformer and CNN modules as an encoder-decoder structure. The encoder incorporates ELSA transformer blocks used to enhance local detailed feature extraction. The extracted feature representations are fed to the decoder part via skip connections. The encoder part includes channel squeeze and spatial excitation blocks, which enable the extracted features to be more informative both spatially and channel-wise. RESULTS: The method is evaluated on the public BraTS 2021 datasets containing 1251 cases of brain images, each with four 3D MRI modalities. Our proposed approach achieved excellent segmentation results with an average Dice score of 89.77% and an average Hausdorff distance of 8.90 mm. CONCLUSION: We developed an automated framework for brain tumor segmentation using Swin transformer and enhanced local self-attention. Experimental results show that our method outperforms state-of-th-art 3D algorithms for brain tumor segmentation.

Biological efficacy of simulated radiolabeled Lipiodol® ultra-fluid and microspheres for various beta emitters: study based on VX2 tumors.

BACKGROUND: Radioembolization is one therapeutic option for the treatment of locally early-stage hepatocellular carcinoma. The aim of this study was to evaluate the distribution of Lipiodol® ultra-fluid and microspheres and to simulate their effectiveness with different beta emitters (90Y, 188Re, 32P, 166Ho, 131I, and 177Lu) on VX2 tumors implanted in the liver of 30 New Zealand rabbits. RESULTS: Twenty-three out of 30 rabbits had exploitable data: 14 in the group that received Lipiodol® ultra-fluid (group L), 6 in the group that received microspheres (group M), and 3 in the control group (group C). The histologic analysis showed that the Lipiodol® ultra-fluid distributes homogeneously in the tumor up to 12 days after injection. The X-ray µCT images showed that Lipiodol® ultra-fluid has a more distal penetration in the tumor than microspheres. The entropy (disorder of the system) in the L group was significantly higher than in the M group (4.06 vs 2.67, p = 0.01). Equivalent uniform biological effective doses (EUBED) for a tumor-absorbed dose of 100 Gy were greater in the L group but without statistical significance except for 177Lu (p = 0.03). The radionuclides ranking by EUBED (from high to low) was 90Y, 188Re, 32P, 166Ho, 131I, and 177Lu. CONCLUSIONS: This study showed a higher ability of Lipiodol® ultra-fluid to penetrate the tumor that translated into a higher EUBED. This study confirms 90Y as a good candidate for radioembolization, although 32P, 166Ho, and 188Re can achieve similar results.

Synergic prognostic value of 3D CT scan subcutaneous fat and muscle masses for immunotherapy-treated cancer.

BACKGROUND: Our aim was to explore the prognostic value of anthropometric parameters in a large population of patients treated with immunotherapy. METHODS: We retrospectively included 623 patients with advanced non-small cell lung cancer (NSCLC) (n=318) or melanoma (n=305) treated by an immune-checkpoint-inhibitor having a pretreatment (thorax-)abdomen-pelvis CT scan. An external validation cohort of 55 patients with NSCLC was used. Anthropometric parameters were measured three-dimensionally (3D) by a deep learning software (Anthropometer3DNet) allowing an automatic multislice measurement of lean body mass, fat body mass (FBM), muscle body mass (MBM), visceral fat mass (VFM) and sub-cutaneous fat mass (SFM). Body mass index (BMI) and weight loss (WL) were also retrieved. Receiver operator characteristic (ROC) curve analysis was performed and overall survival was calculated using Kaplan-Meier (KM) curve and Cox regression analysis. RESULTS: In the overall cohort, 1-year mortality rate was 0.496 (95% CI: 0.457 to 0.537) for 309 events and 5-year mortality rate was 0.196 (95% CI: 0.165 to 0.233) for 477 events. In the univariate Kaplan-Meier analysis, prognosis was worse (p<0.001) for patients with low SFM (<3.95 kg/m2), low FBM (<3.26 kg/m2), low VFM (<0.91 kg/m2), low MBM (<5.85 kg/m2) and low BMI (<24.97 kg/m2). The same parameters were significant in the Cox univariate analysis (p<0.001) and, in the multivariate stepwise Cox analysis, the significant parameters were MBM (p<0.0001), SFM (0.013) and WL (0.0003). In subanalyses according to the type of cancer, all body composition parameters were statistically significant for NSCLC in ROC, KM and Cox univariate analysis while, for melanoma, none of them, except MBM, was statistically significant. In multivariate Cox analysis, the significant parameters for NSCLC were MBM (HR=0.81, p=0.0002), SFM (HR=0.94, p=0.02) and WL (HR=1.06, p=0.004). For NSCLC, a KM analysis combining SFM and MBM was able to separate the population in three categories with the worse prognostic for the patients with both low SFM (<5.22 kg/m2) and MBM (<6.86 kg/m2) (p<0001). On the external validation cohort, combination of low SFM and low MBM was pejorative with 63% of mortality at 1 year versus 25% (p=0.0029). CONCLUSIONS: 3D measured low SFM and MBM are significant prognosis factors of NSCLC treated by immune checkpoint inhibitors and can be combined to improve the prognostic value.

Evaluation of the capability and reproducibility of RECIST 1.1. measurements by technologists in breast cancer follow-up: a pilot study.

The evaluation of tumor follow-up according to RECIST 1.1 has become essential in clinical practice given its role in therapeutic decision making. At the same time, radiologists are facing an increase in activity while facing a shortage. Radiographic technologists could contribute to the follow-up of these measures, but no studies have evaluated their ability to perform them. Ninety breast cancer patients were performed three CT follow-ups between September 2017 and August 2021. 270 follow-up treatment CT scans were analyzed including 445 target lesions. The rate of agreement of classifications RECIST 1.1 between five technologists and radiologists yielded moderate (k value between 0.47 and 0.52) and substantial (k value = 0.62 and k = 0.67) agreement values. 112 CT were classified as progressive disease (PD) by the radiologists, and 414 new lesions were identified. The analysis showed a percentage of strict agreement of progressive disease classification between reader-technologists and radiologists ranging from substantial to almost perfect agreement (range 73-97%). Analysis of intra-observer agreement was strong at almost perfect (k > 0.78) for 3 technologists. These results are encouraging regarding the ability of selected technologists to perform measurements according to RECIST 1.1 criteria by CT scan with good identification of disease progression.

Overview of the HECKTOR Challenge at MICCAI 2022: Automatic Head and Neck Tumor Segmentation and Outcome Prediction in PET/CT.

This paper presents an overview of the third edition of the HEad and neCK TumOR segmentation and outcome prediction (HECKTOR) challenge, organized as a satellite event of the 25th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2022. The challenge comprises two tasks related to the automatic analysis of FDG-PET/CT images for patients with Head and Neck cancer (H&N), focusing on the oropharynx region. Task 1 is the fully automatic segmentation of H&N primary Gross Tumor Volume (GTVp) and metastatic lymph nodes (GTVn) from FDG-PET/CT images. Task 2 is the fully automatic prediction of Recurrence-Free Survival (RFS) from the same FDG-PET/CT and clinical data. The data were collected from nine centers for a total of 883 cases consisting of FDG-PET/CT images and clinical information, split into 524 training and 359 test cases. The best methods obtained an aggregated Dice Similarity Coefficient (DSCagg) of 0.788 in Task 1, and a Concordance index (C-index) of 0.682 in Task 2.

ESTIMation of the ABiLity of prophylactic central compartment neck dissection to modify outcomes in low-risk differentiated thyroid cancer: a prospective randomized trial.

BACKGROUND: Prophylactic central neck dissection in clinically low-risk cT1bT2N0 papillary thyroid carcinoma is controversial, due to a large number of conflicting retrospective studies, some showing an advantage in terms of locoregional recurrence, others showing no advantage. These previous studies all show high rates of excellent response. We aim to demonstrate the non-inferiority of thyroidectomy alone as compared to total thyroidectomy with prophylactic central neck dissection in conjunction with adjuvant RAI 30 mCi with rTSH stimulation in terms of excellent response at 1 year. TRIAL DESIGN AND METHODS: Prospective randomized open multicenter phase III trial including patients with 11-40-mm papillary thyroid carcinoma (Bethesda VI) or suspicious cytology (Bethesda V) confirmed malignant on intra-operative frozen section analysis, with no suspicious lymph nodes on a specialized preoperative ultrasound examination. Patients will be randomized 1:1 into two groups: the reference group total thyroidectomy with bilateral prophylactic central neck dissection, and the comparator group total thyroidectomy alone. All patients will receive an ablative dose of 30mCi of radioactive iodine (RAI) within 4 months of surgery. The primary outcome is to compare the rate of excellent response at 1 year after surgery between the groups, as defined by an unstimulated serum thyroglobulin (Tg) level ≤ 0.2 ng/mL with no anti-Tg antibodies, an normal neck ultrasound and no ectopic uptake on the post-RAI scintiscan. Non-inferiority will be demonstrated if the rate of patients with excellent response at 1 year after randomization does not differ by more than 5%. Setting the significance level at 0.025 (one-sided) and a power of 80% requires a sample size of 598 patients (299 per group). Secondary outcomes are to compare Tg levels at 8 +/- 2 postoperative weeks, before RAI ablation, the rate of excellent response at 3 and 5 years, the rate of other responses at 1, 3, and 5 years (biochemical incomplete, indeterminate, and structurally incomplete responses), complications, quality of life, and cost-utility. DISCUSSION (POTENTIAL IMPLICATIONS): If non-inferiority is demonstrated with this high-level evidence, prophylactic neck dissection will have been shown to not be necessary in clinically low-risk papillary thyroid carcinoma. TRIAL REGISTRATION: NCT03570021. June 26,2018.

Respiratory muscle metabolic activity on PET/CT correlates with obstructive ventilatory defect severity and prognosis in patients undergoing lung cancer surgery.

BACKGROUND AND OBJECTIVE: Respiratory muscle activity is increased in patients with chronic respiratory disease. 18 F-FDG-PET/CT can assess respiratory muscle activity. We hypothesized that respiratory muscles metabolism was correlated to lung function impairment and was associated to prognosis in patients undergoing lung cancer surgery based on the research question whether respiratory muscle metabolism quantitatively correlates with the severity of lung function impairment in patients? Does respiratory muscle hypermetabolism have prognostic value? METHODS: Patients undergoing 18 F-FDG-PET/CT and pulmonary function tests prior to lung cancer surgery were identified. Maximum Standardized Uptake Value (SUVm) were measured in each respiratory muscle group (sternocleidomastoid, scalene, intercostal, diaphragm), normalized against deltoid SUVm. Respiratory muscle hypermetabolism was defined as SUVm >90th centile in any respiratory muscle group. Clinical outcomes were collected from a prospective cohort. RESULTS: One hundred fifty-six patients were included, mostly male [110 (71%)], 53 (34%) with previous diagnosis of COPD. Respiratory muscle SUVm were: scalene: 1.84 [1.51-2.25], sternocleidomastoid 1.64 [1.34-1.95], intercostal 1.01 [0.84-1.16], diaphragm 1.79 [1.41-2.27]. Tracer uptake was inversely correlated to FEV1 for the scalene (r = -0.29, p < 0.001) and SCM (r = -0.17, p = 0.03) respiratory muscle groups and positively correlated to TLC for the scalene (r = 0.17, p = 0.04). Respiratory muscle hypermetabolism was found in 45 patients (28.8%), who had a lower VO2 max (15.4 [14.2-17.5] vs. 17.2 mL/kg/min [15.2-21.1], p = 0.07) and poorer overall survival when adjusting to FEV1% (p < 0.01). CONCLUSION: Our findings show respiratory muscle hypermetabolism is associated with lung function impairment and has prognostic significance. 18 F-FDG/PET-CT should be considered as a tool for assessing respiratory muscle activity and to identify high-risk patients.

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.

Advances in PET and MRI imaging of tumor hypoxia.

Tumor hypoxia is a complex and evolving phenomenon both in time and space. Molecular imaging allows to approach these variations, but the tracers used have their own limitations. PET imaging has the disadvantage of low resolution and must take into account molecular biodistribution, but has the advantage of high targeting accuracy. The relationship between the signal in MRI imaging and oxygen is complex but hopefully it would lead to the detection of truly oxygen-depleted tissue. Different ways of imaging hypoxia are discussed in this review, with nuclear medicine tracers such as [18F]-FMISO, [18F]-FAZA, or [64Cu]-ATSM but also with MRI techniques such as perfusion imaging, diffusion MRI or oxygen-enhanced MRI. Hypoxia is a pejorative factor regarding aggressiveness, tumor dissemination and resistance to treatments. Therefore, having accurate tools is particularly important.

Body Composition to Define Prognosis of Cancers Treated by Anti-Angiogenic Drugs.

Background: Body composition could help to better define the prognosis of cancers treated with anti-angiogenics. The aim of this study is to evaluate the prognostic value of 3D and 2D anthropometric parameters in patients given anti-angiogenic treatments. Methods: 526 patients with different types of cancers were retrospectively included. The software Anthropometer3DNet was used to measure automatically fat body mass (FBM3D), muscle body mass (MBM3D), visceral fat mass (VFM3D) and subcutaneous fat mass (SFM3D) in 3D computed tomography. For comparison, equivalent two-dimensional measurements at the L3 level were also measured. The area under the curve (AUC) of the receiver operator characteristics (ROC) was used to determine the parameters' predictive power and optimal cut-offs. A univariate analysis was performed using Kaplan−Meier on the overall survival (OS). Results: In ROC analysis, all 3D parameters appeared statistically significant: VFM3D (AUC = 0.554, p = 0.02, cutoff = 0.72 kg/m2), SFM3D (AUC = 0.544, p = 0.047, cutoff = 3.05 kg/m2), FBM3D (AUC = 0.550, p = 0.03, cutoff = 4.32 kg/m2) and MBM3D (AUC = 0.565, p = 0.007, cutoff = 5.47 kg/m2), but only one 2D parameter (visceral fat area VFA2D AUC = 0.548, p = 0.034). In log-rank tests, low VFM3D (p = 0.014), low SFM3D (p < 0.0001), low FBM3D (p = 0.00019) and low VFA2D (p = 0.0063) were found as a significant risk factor. Conclusion: automatic and 3D body composition on pre-therapeutic CT is feasible and can improve prognostication in patients treated with anti-angiogenic drugs. Moreover, the 3D measurements appear to be more effective than their 2D counterparts.

Using 18F-FDG-PET/CT Metrics to Predict Survival in Ra-Dio-Iodine Refractory Thyroid Cancers.

Radio-iodine refractory (RAI-R) differentiated thyroid cancer (DTC) is a rare disease with a poor prognosis and limited therapeutic resources. Therefore, identifying prognostic factors is essential in order to select patients who could benefit from an early start of treatment. The aim of this study is to identify positron emission tomography with 18F-fluorodeoxyglucose with integrated computed tomography (18F-FDG-PET/CT) parameters to predict overall survival (OS) in patients with RAI-R DTC. In this single-center retrospective study, we analyze the 18F-FDG-PET/CT parameters of 34 patients with RAI-R DTC between April 2007 and December 2019. The parameters collected are MTV, SUVmax and progression for each site of metastasis (neck, mediastinum, lungs, liver, bone) and total sites. ROC curves, Kaplan-Meier survival analysis curves, univariate and multivariate Cox analyses determine prognostic factors for 1-year and 5-year OS. The parameters for mediastinum, liver and total sites are significantly associated with worse 1-year and 5-year OS by both ROC curve analysis and Kaplan-Meier survival analysis. Univariate Cox analysis confirms significance of mediastinum SUVmax (HR 1.08; 95% CI [1.02-1.15]; p = 0.014) and total SUVmax (HR 1.06; 95% CI [1-1.12]; p = 0.042) for worse 1-year OS; of mediastinum SUVmax (HR 1.06; 95% CI [1.02-1.10]; p = 0.003), liver SUVmax (HR 1.04; 95% CI [1.01-1.08]; p = 0.02), liver MTV (HR 2.56; 95% CI [1.13-5.82]; p = 0.025), overall SUVmax (HR 1.05; 95% CI [1.02-1.08]; p = 0.001) and total MTV (HR 1.41; 95% CI [1.07-1.86]; p = 0.016) for worse 5-year OS. Multivariate Cox analysis confirms a significant association between liver MTV (HR 1.02; 95% CI [1-1.04]; p = 0.042) and decrease 1-year OS. In this study, we demonstrate that in RAI-R DTC, 18F-FDG-PET/CT parameters of the mediastinum, liver and overall tumor burden were prognostic factors of poor 1-year and 5-year OS. Identifying these criteria could allow early therapeutic intervention in order to improve patients' survival.

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.

UMI-Varcal: A Low-Frequency Variant Caller for UMI-Tagged Paired-End Sequencing Data.

The rapid transition from traditional sequencing methods to Next-Generation Sequencing (NGS) has allowed for a faster and more accurate detection of somatic variants (Single-Nucleotide Variant (SNV) and Copy Number Variation (CNV)) in tumor cells. NGS technologies require a succession of steps during which false variants can be silently added at low frequencies. Filtering these artifacts can be a rather difficult task especially when the experiments are designed to look for very low frequency variants. Recently, adding unique molecular barcodes called UMI (Unique Molecular Identifier) to the DNA fragments appears to be a very effective strategy to specifically filter out false variants from the variant calling results (Kukita et al. DNA Res 22(4):269-277, 2015; Newman et al. Nat Biotechnol 34(5):547-555, 2016; Schmitt et al. Proc Natl Acad Sci U S A 109(36):14508-14513). Here, we describe UMI-VarCal (Sater et al. Bioinformatics 36:2718-2724, 2020), which can use the UMI information from UMI-tagged reads to offer a faster and more accurate variant calling analysis.

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.

Synthetic MRI for Radiotherapy Planning for Brain and Prostate Cancers: Phantom Validation and Patient Evaluation.

Purpose: We aimed to evaluate the accuracy of T 1 and T 2 mappings derived from a multispectral pulse sequence (magnetic resonance image compilation, MAGiC®) on 1.5-T MRI and with conventional sequences [gradient echo with variable flip angle (GRE-VFA) and multi-echo spin echo (ME-SE)] compared to the reference values for the purpose of radiotherapy treatment planning. Methods: The accuracy of T 1 and T 2 measurements was evaluated with 2 coils [head and neck unit (HNU) and BODY coils] on phantoms using descriptive statistics and Bland-Altman analysis. The reproducibility and repeatability of T 1 and T 2 measurements were performed on 15 sessions with the HNU coil. The T 1 and T 2 synthetic sequences obtained by both methods were evaluated according to quality assurance (QA) requirements for radiotherapy. T 1 and T 2 in vivo measurements of the brain or prostate tissues of two groups of five subjects were also compared. Results: The phantom results showed good agreement (mean bias, 8.4%) between the two measurement methods for T 1 values between 490 and 2,385 ms and T 2 values between 25 and 400 ms. MAGiC® gave discordant results for T 1 values below 220 ms (bias with the reference values, from 38% to 1,620%). T 2 measurements were accurately estimated below 400 ms (mean bias, 8.5%) by both methods. The QA assessments are in agreement with the recommendations of imaging for contouring purposes for radiotherapy planning. On patient data of the brain and prostate, the measurements of T 1 and T 2 by the two quantitative MRI (qMRI) methods were comparable (max difference, <7%). Conclusion: This study shows that the accuracy, reproducibility, and repeatability of the multispectral pulse sequence (MAGiC®) were compatible with its use for radiotherapy treatment planning in a range of values corresponding to soft tissues. Even validated for brain imaging, MAGiC® could potentially be used for prostate qMRI.

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.