Search Results (905)

Background/Objectives: Accurate diagnosis of brain tumors is one of the most important challenges in neuro-oncology since tumor classification and volumetric segmentation inform treatment planning. Two-dimensional classification and three-dimensional segmentation deep learning models can augment radiological workflows, particularly if paired with explainable AI techniques to improve model interpretability. The objective of this research was to develop a web-based brain tumor segmentation and classification diagnosis platform. Methods: A diagnosis system was developed combining 2D tumor classification and 3D volumetric segmentation. Classification employed a fine-tuned MobileNetV2 model trained on a glioma, meningioma, pituitary tumor, and normal control dataset. Segmentation employed a SegResNet model trained on BraTS multi-channel MRI with synthetic no-tumor data. A meta-classifier MLP was used for binary tumor detection from volumetric features. Explainability was offered using XRAI maps for 2D predictions and Gaussian overlays for 3D visualizations. The platform was incorporated into a web interface for clinical use. Results: MobileNetV2 2D model recorded 98.09% classification accuracy for tumor classification. 3D SegResNet obtained Dice coefficients around 68–70% for tumor segmentations. The MLP-based tumor detection module recorded 100% detection accuracy. Explainability modules could identify the area of the tumor, and saliency and overlay maps were consistent with real pathological features in both 2D and 3D. Conclusions: Deep learning diagnosis system possesses improved brain tumor classification and segmentation with interpretable outcomes by utilizing XAI techniques. Deployment as a web tool and a user-friendly interface made it suitable for clinical usage in radiology workflows. Full article

Background/Objectives: Pituitary tumors account for over 90% of all sellar region masses. However, a spectrum of rare neoplastic, inflammatory, infectious, and vascular lesions—benign and malignant—can arise in the intra- and parasellar compartments and clinically and radiologically mimic PitNETs. We report a cohort of 47 such rare and cystic midline intracranial lesions, emphasizing their distinctive morphological, clinical, and imaging features and the personalized treatment strategies applied. Methods: In this retrospective single-center study, we reviewed all patients treated for suspected PitNETs via transsphenoidal approach between 2015 and 2024. Of 529 surgical cases, we excluded confirmed PitNETs, meningiomas, and classical intradural craniopharyngiomas. Collected data encompassed patient demographics, tumor characteristics, presenting symptoms, extent of resection or medical therapy, endocrine outcomes, and follow-up information. Results: Among all 529 patients who underwent surgical treatment for sellar lesions from 2015 to 2024, 47 cases (8.9%) were identified as rare or cystic masses. Forty-six underwent transsphenoidal resection; one patient with hypophysitis received corticosteroid therapy alone. Presenting symptoms included headache (n = 16), dizziness (n = 5), oculomotor disturbances (n = 2), and visual impairment (n = 17). Endocrine dysfunction was found in 30 patients, 27 of whom required hydrocortisone replacement. Histopathological diagnoses were led by colloid cysts (n = 14) and Rathke’s cleft cysts (n = 11). The remaining 22 cases comprised plasmacytoma, germinoma, lymphoma, pituicytoma, inverted papilloma, metastatic carcinoma, chordoma, nasopharyngeal carcinoma, chloroma, and other rare entities. Preoperative imaging diagnosis proved incorrect in 38% (18/47) of cases, with several lesions initially misidentified as PitNETs. Conclusions: Nearly 9% of presumed PitNETs were rare, often benign or inflammatory lesions requiring distinct management. Most could be safely resected and demonstrated excellent long-term outcomes. Yet, despite advanced imaging techniques, accurate preoperative differentiation remains challenging, with over one-third misdiagnosed. Clinical red flags—such as early hormone deficits, rapid progression or atypical imaging findings—should prompt early interdisciplinary evaluation and, when indicated, image-guided biopsy to avoid unnecessary surgery and ensure tailored therapy. Full article

Background: Anti-synthetase Syndrome (ASyS) is an idiopathic inflammatory myopathy characterized by muscle weakness and inflammatory infiltrates in muscles. Sjogren’s disease (SD) is an autoimmune condition primarily affecting exocrine glands. Both these conditions may present lung involvement. We describe a female patient with anti-synthetase/SD overlap syndrome and review the literature to identify published cases describing this overlap, aiming to better define its clinical, radiological, and serological features. Methods: The case description was based on a retrospective collection of clinical, laboratory, and imaging data related to the patient’s diagnostic process and clinical course. Data were anonymized and handled in accordance with the competent territorial Ethics Committee. A literature review was performed using the MEDLINE and Scopus databases by combining the keywords “Anti-Synthetase syndrome”, “Sjögren disease”, “Sjögren syndrome”, “Myositis”, and “Interstitial lung disease” (ILD). Published cases were selected if they met the 2016 EULAR/ACR criteria for SD and at least one of the currently proposed classification criteria for ASyS. Results: The described case concerns a 68-year-old woman with rapidly progressive ILD. The diagnosis of anti-synthetase/SD overlap syndrome was based on clinical, serological (anti-Ro52 and anti-PL7 antibodies), histological, and radiological findings. Despite immunosuppressive and antifibrotic treatment, the clinical course worsened, leading to a poor outcome. In addition, six relevant cases were identified in the literature. Clinical presentations, autoantibody profiles, radiological findings, and outcomes were highly heterogeneous. Among the reported cases, no standardized treatment protocols were adopted, reflecting the lack of consensus in managing this rare condition. Conclusions: In anti-synthetase/SD overlap syndrome, ILD may follow a rapidly progressive course. Early recognition can be challenging, especially in the absence of muscular involvement. This case-based review highlights the need for more standardized approaches to the diagnosis and management of this rare and complex overlap syndrome. Full article

Background: Pigmented superficial skin lesions pose a persistent diagnostic challenge due to overlapping clinical and dermoscopic appearances between benign and malignant entities. While histopathology remains the gold standard, there is growing interest in non-invasive imaging models that can preoperatively stratify malignancy risk. This methodological pilot study was designed to explore the feasibility and initial diagnostic performance of a novel radiology-adapted logistic regression approach. To develop and preliminarily evaluate a new logistic model integrating both structural (lesion size, depth) and vascular (Doppler patterns) ultrasonographic features for non-invasive risk stratification of pigmented superficial skin lesions. Material and Methods: In this prospective single-center pilot investigation, 44 patients underwent standardized high-frequency grayscale and Doppler ultrasound prior to excisional biopsy. Lesion size, depth, and vascularity patterns were systematically recorded. Three logistic regression models were constructed: (1) based on lesion size and depth, (2) based on vascularity patterns alone, and (3) combining all parameters. Model performance was assessed via ROC curve analysis. Intra-observer reliability was determined by repeated measurements on a random subset. Results: The lesion size and depth model yielded an AUC of 0.79, underscoring the role of structural features. The vascularity-only model showed an AUC of 0.76. The combined model demonstrated superior discriminative ability, with an AUC of approximately 0.85. Intra-observer analysis confirmed excellent repeatability (κ > 0.80; ICC > 0.85). Conclusions: This pilot study introduces a novel logistic framework that combines grayscale and Doppler ultrasound parameters to enhance non-invasive malignancy risk assessment in pigmented superficial skin lesions. These encouraging initial results warrant larger multicenter studies to validate and refine this promising approach. Full article

Background/Objectives: Multimodal large language models (LLMs) are increasingly used in radiology. However, their ability to recognize fundamental imaging features, including modality, anatomical region, imaging plane, contrast-enhancement status, and particularly specific magnetic resonance imaging (MRI) sequences, remains underexplored. This study aims to evaluate and compare the performance of three advanced multimodal LLMs (ChatGPT-4o, Claude 4 Opus, and Gemini 2.5 Pro) in classifying brain MRI sequences. Methods: A total of 130 brain MRI images from adult patients without pathological findings were used, representing 13 standard MRI series. Models were tested using zero-shot prompts for identifying modality, anatomical region, imaging plane, contrast-enhancement status, and MRI sequence. Accuracy was calculated, and differences among models were analyzed using Cochran’s Q test and McNemar test with Bonferroni correction. Results: ChatGPT-4o and Gemini 2.5 Pro achieved 100% accuracy in identifying the imaging plane and 98.46% in identifying contrast-enhancement status. MRI sequence classification accuracy was 97.7% for ChatGPT-4o, 93.1% for Gemini 2.5 Pro, and 73.1% for Claude 4 Opus (p < 0.001). The most frequent misclassifications involved fluid-attenuated inversion recovery (FLAIR) sequences, often misclassified as T1-weighted or diffusion-weighted sequences. Claude 4 Opus showed lower accuracy in susceptibility-weighted imaging (SWI) and apparent diffusion coefficient (ADC) sequences. Gemini 2.5 Pro exhibited occasional hallucinations, including irrelevant clinical details such as “hypoglycemia” and “Susac syndrome.” Conclusions: Multimodal LLMs demonstrate high accuracy in basic MRI recognition tasks but vary significantly in specific sequence classification tasks. Hallucinations emphasize caution in clinical use, underlining the need for validation, transparency, and expert oversight. Full article

Purpose: Predicting colorectal cancer liver metastasis (CRLM) is essential for prognostic assessment. This study aims to develop and validate an interpretable multimodal machine learning framework based on multiparametric MRI for predicting CRLM, and to enhance the clinical interpretability of the model through SHapley Additive exPlanations (SHAP) analysis and deep learning visualization. Methods: This multicenter retrospective study included 463 patients with pathologically confirmed colorectal cancer from two institutions, divided into training (n = 256), internal testing (n = 111), and external validation (n = 96) sets. Radiomics features were extracted from manually segmented regions on axial T2-weighted imaging (T2WI) and diffusion-weighted imaging (DWI). Deep learning features were obtained from a pretrained ResNet101 network using the same MRI inputs. A least absolute shrinkage and selection operator (LASSO) logistic regression classifier was developed for clinical, radiomics, deep learning, and combined models. Model performance was evaluated by AUC, sensitivity, specificity, and F1-score. SHAP was used to assess feature contributions, and Grad-CAM was applied to visualize deep feature attention. Results: The combined model integrating features across the three modalities achieved the highest performance across all datasets, with AUCs of 0.889 (training), 0.838 (internal test), and 0.822 (external validation), outperforming single-modality models. Decision curve analysis (DCA) revealed enhanced clinical net benefit from the integrated model, while calibration curves confirmed its good predictive consistency. SHAP analysis revealed that radiomic features related to T2WI texture (e.g., LargeDependenceLowGrayLevelEmphasis) and clinical biomarkers (e.g., CA19-9) were among the most predictive for CRLM. Grad-CAM visualizations confirmed that the deep learning model focused on tumor regions consistent with radiological interpretation. Conclusions: This study presents a robust and interpretable multiparametric MRI-based model for noninvasively predicting liver metastasis in colorectal cancer patients. By integrating handcrafted radiomics and deep learning features, and enhancing transparency through SHAP and Grad-CAM, the model provides both high predictive performance and clinically meaningful explanations. These findings highlight its potential value as a decision-support tool for individualized risk assessment and treatment planning in the management of colorectal cancer. Full article

Background: Identifying the etiological factors of syringomyelia, which can cause progressive neurological deficits in the spinal cord, is critically important for both diagnosis and treatment. This study aimed to assess the cranial morphometric features of patients with idiopathic syringomyelia by conducting comparative analyses with individuals diagnosed with Chiari Type I, Chiari Type I accompanied by syringomyelia, and healthy controls, in order to elucidate the potential structural contributors to the pathogenesis of idiopathic syringomyelia. Methods: In this retrospective and comparative study, a total of 172 patients diagnosed with Chiari Type I and/or syringomyelia between 2016 and 2024, along with 156 radiologically normal individuals, were included. The participants were categorized into four groups: healthy controls, Chiari Type I, Chiari Type I with syringomyelia, and idiopathic syringomyelia (defined as syringomyelia without an identifiable cause). Midline sagittal T1-weighted MR images were used to obtain quantitative measurements of the posterior fossa, cerebellum, intracranial area, and foramen magnum. All measurements were stratified and statistically analyzed by sex. Results: In cases with idiopathic syringomyelia, both the posterior fossa area and the cerebellum/posterior fossa ratio differed significantly from those of healthy controls. In male patients, the foramen magnum diameter was significantly larger in the Chiari + syringomyelia group compared with the idiopathic group. A significant correlation was found between the degree of tonsillar descent and selected morphometric parameters in female subjects, whereas no such correlation was observed in males. Both Chiari groups exhibited significantly smaller posterior fossa dimensions compared with the healthy and idiopathic groups, indicating greater neural crowding. Additionally, in Chiari Type I patients, increasing degrees of tonsillar descent were associated with a decreased incidence of syringomyelia. Conclusions: Anatomical variations such as a reduced posterior fossa area or altered foramen magnum diameter may contribute to the pathogenesis of idiopathic syringomyelia. Cranial morphometric analysis appears to offer diagnostic value in these cases. Further prospective, multicenter studies incorporating advanced neuroimaging modalities, particularly those assessing cerebrospinal fluid dynamics, are warranted to better understand the mechanisms underlying syringomyelia of unknown etiology. Full article

Objectives: Oncocyte-rich indeterminate thyroid nodules (O-ITNs) present diagnostic and management challenges due to overlapping features between benign and malignant lesions and differing cytological classifications. This study aimed primarily to assess the ultrasound (US) characteristics and US-based risk of O-ITNs using the American College of Radiology Thyroid Imaging Reporting And Data Systems (ACR TI-RADS). A secondary objective was to compare the Bethesda System for Reporting Thyroid Cytopathology (BSRTC) and Italian Consensus for the Classification and Reporting of Thyroid Cytology (ICCRTC) cytological systems regarding classification and clinical management implications for O-ITNs. Methods: A retrospective study was conducted on 177 ITNs (TIR3A and TIR3B) evaluated between June 2023 and December 2024 at CTO-Alesini, Rome (Italy). Nodules were assessed with US, cytology, and histology. Oncocyte predominance was defined as >70% oncocytes on fine-needle aspiration (FNA). US features were analyzed according to ACR TI-RADS. Nodules were reclassified by BSRTC, and potential differences in clinical case management (CCM) were analyzed. Results: O-ITNs comprised 47.5% of the sample. Compared to non-O-ITNs, O-ITNs were larger and more frequently showed low-risk US features, including a higher prevalence of ACR TI-RADS 3 nodules. However, no progressive increase in the risk of malignancy (ROM) was observed across ACR TI-RADS classes within O-ITNs. Histological malignancy was identified in 47.1% of O-ITNs, a lower proportion compared to non-O-ITNs, though the difference was not statistically significant. Classification discordance with potential management impact was lower in O-ITNs (20.2%) than in non-O-ITNs (38.7%). Conclusions: O-ITNs typically exhibit benign-appearing US features and lower classification discordance between BSRTC and ICCRTC, yet US risk stratification fails to differentiate malignancy risk within O-ITNs. A tailored approach integrating cytology and cautious US interpretation is essential for optimal O-ITN management. Full article

Background: Pseudoprogression is known to occur after immune-checkpoint inhibitor (ICI) therapy in brain metastasis and can complicate clinical decision-making. Still, its incidence, timing, and clinical presentation remain unclear. A retrospective cohort study in melanoma and non-small cell lung cancer brain metastasis patients was conducted to address this. Materials and Methods: Brain metastasis patients showing progression on MRI according to response assessment in neuro-oncology brain metastases criteria after starting ICI therapy were included, irrespective of prior irradiation. Lesions were classified as tumour progression (TP) or pseudoprogression based on three-month radiological follow-up or histopathology. TP was assigned if progression was again shown at three months. Pseudoprogression was assigned if lesions showed stability, partial, or complete response at three months. ‘Non-classified’ lesions were those with new or changed treatment during follow-up. Results: A cohort of 98 patients with 233 lesions was included over a 13-year period; 170 lesions were considered non-classified, and 41 and 22 lesions were classified as TP and pseudoprogression respectively. This resulted in a lesion- and patient-specific incidence for pseudoprogression of 9.4% and 17.3% respectively. Due to the large number of lesions that could not be classified, as is the case in clinical practice, the reported incidence in this study is likely an underestimation and can be seen as a ‘minimum’ incidence rate. Ten pseudoprogression (45.5%) and 13 (31.7%) TP lesions were previously irradiated. Pseudoprogression occurred at a median of 2.7 months after starting ICI therapy. The only clinical feature distinguishing patients with TP from pseudoprogression was that TP patients were more likely to need dexamethasone for neurological symptoms. Conclusions: Pseudoprogression has a lesion-specific incidence rate of at least 9.4% and occurs at a median of 2.7 months after starting ICI therapy. Severe neurological symptoms requiring dexamethasone may be a clinical feature typical for TP. Full article

Oligometastasis represents a clinically relevant state of limited metastatic disease that could be amenable to selected local therapies in carefully chosen patients. Although initial trials such as SABR-COMET demonstrated a survival benefit with aggressive local treatment, breast cancer was underrepresented. Subsequent breast cancer-specific trials, including NRG-BR002, failed to show a clear survival benefit, highlighting uncertainties and the need for further refinement in patient selection and integration with systemic approaches. The definitions of oligometastasis continue to evolve, incorporating radiological, clinical, and biological features. Advances in imaging and molecular profiling suggest that oligometastatic breast cancer might represent a distinct biological subtype, with potential biomarkers including PIK3CA mutations and YAP/TAZ expression. Organ-specific strategies using stereotactic radiotherapy, surgery, and proton therapy have shown favorable local control in certain settings, though their impact on the overall survival remains under investigation. Emerging techniques, including circulating tumor DNA (ctDNA) analysis, are being explored to improve patient selection and disease monitoring. Ongoing trials may provide further insight into the role of local therapy, particularly in hormone receptor-positive or HER2-positive subtypes. Local and systemic strategies need to be carefully coordinated to optimize the outcomes. This review summarizes the current definitions of and evidence and therapeutic considerations for oligometastatic breast cancer and outlines potential future directions. Full article

Introduction: Pertussis, a vaccine-preventable disease caused by Bordetella pertussis, is resurging globally due to declining immunization rates. This study explores the clinical and epidemiological features of pediatric pertussis cases in a regional Romanian hospital amid growing vaccine hesitancy. Methods: We conducted a retrospective cohort study on 99 children diagnosed with pertussis and admitted to Ploiești Pediatric Hospital between January 2024 and January 2025. Demographic, clinical, laboratory, and radiological data were analyzed using SPSS 25.0. Results: The median age was 11 months (IQR 4–25), with 12.1% under two months, and ineligible for the first DTaP dose. Notably, 72.7% of children were unvaccinated; 59.4% had missed scheduled doses. None of the mothers received the DTaP vaccination during pregnancy. Most cases (55.6%) had bilaterally accentuated interstitial patterns on chest X-ray, significantly associated with vaccination status (p = 0.019). The leukocyte count was higher in children with alveolar infiltrates (p = 0.028), and as the number of vaccine doses increased, the leukocyte count tended to slightly decrease (p = 0.022, R = −0.229). PCR confirmation was obtained after a mean of 2.2 days, with 12.1% of cases confirmed post-discharge. Azithromycin was used in 74.7% of cases, with good tolerability. Conclusions: Low pediatric and maternal vaccine uptake was a major contributor to pertussis resurgence in this cohort. Radiological severity correlated with vaccination status, suggesting that vaccination may confer protection not only against infection but also against severe pulmonary involvement. These findings support urgent public health efforts to restore vaccine confidence and coverage, particularly among vulnerable infant populations and expectant mothers. Full article

Spondyloepimetaphyseal dysplasia type Isidor-Toutain (RPL13-SEMD) is an autosomal dominant skeletal dysplasia caused by heterozygous pathogenic variants in the RPL13 gene, encoding the ribosomal protein eL13. To date, 13 pathogenic variants in RPL13 have been reported, all clustering within intron 5 and exon 6, suggesting this hotspot region is critical for the function of ribosomes in skeletal tissues. Here, we present clinical and radiological characteristics of seven individuals, five children and two adults, from four unrelated families with RPL13-SEMD caused by two novel variants (c.477+5G>C and c.539_541del) and two previously reported variants (c.477+1G>C and c.548G>A) in RPL13. RNA analysis demonstrated that c.477+5G>C leads to a 54-nucleotide extension of exon 5, resulting in an 18-amino acid insertion. The phenotypic spectrum ranged from mild manifestations, such as Blount-like tibial deformity without significant short stature or Perthes-like femoral epiphyseal changes, to severe skeletal deformities with disproportionate short stature, accompanied by extraskeletal features (e.g., penoscrotal hypospadias, coccygeal abnormalities). For the first time, we describe Blount-like tibial deformity as a feature of this dysplasia, which resolves with age. Our study provides additional insights into the clinical, radiological, and genotypic features of RPL13-SEMD through detailed analysis of patients and their affected relatives. Full article

Background and Aim: Syphilis, caused by Treponema pallidum, classically presents with genital or anal chancres; rectal involvement is rare and frequently misdiagnosed as inflammatory bowel disease or malignancy. We describe an unusually severe case of syphilitic proctitis in the setting of advanced HIV-related immunosuppression (CD4 39 cells/µL), in which targeted immunophenotyping (ERG and CD38) was a valuable adjunctive tool in the differential diagnosis. Case Presentation: A 46-year-old man with a recent history of erosive gastritis and esophageal candidiasis presented after six months of unintentional 20 kg weight loss, profound fatigue, intermittent fevers, profuse diarrhea, and two episodes of hematemesis. Workup revealed a new diagnosis of HIV infection (CD4: 39 cells/µL; viral load: 87,837 copies/mL). Contrast-enhanced CT demonstrated uniform, concentric rectal wall thickening (“target sign”). Colonoscopic biopsy showed exuberant granulation tissue and dense plasma cell infiltrates. Immunohistochemistry revealed a dense infiltrate of CD38-positive plasma cells and ERG-positive endothelial proliferation. These findings, in the context of positive serology, were highly supportive of a spirochetal etiology and helped differentiate it from potential mimics. Serology was positive for latent late syphilis (VDRL 1:64). The patient received three weekly doses of intramuscular benzathine penicillin; lumbar puncture excluded neurosyphilis. Discussion: This is among the first reported cases of syphilitic proctitis in a patient with CD4 < 50 cells/µL, where advanced immunophenotyping differentiated syphilitic inflammation from neoplastic or inflammatory mimics. Profound immunosuppression accelerates disease progression and yields atypical clinical features. Conclusion: In HIV-infected patients with chronic rectal symptoms, especially those with CD4 < 50 cells/µL, syphilitic proctitis must be considered. Integration of radiologic assessment, histopathology with ERG/CD38 staining, and serologic testing permits prompt diagnosis. Early benzathine penicillin therapy and rigorous clinical and serologic follow-up are essential to prevent complications, including neurosyphilis. Full article

Background/Objectives: The co-existence of multiple compression sites on the same nerve can pose a clinical and diagnostic challenge, warranting a different treatment strategy. This so-called double crush syndrome (DCS) has mainly been investigated in the upper limb. Only a few studies have investigated DCS for the lower limb. In this article, a single-center illustrative clinical case series is presented, and current literature on L5 nerve root (NR) and concomitant common peroneal nerve (CPN) is reviewed. Methods: All patients presenting between 2019 and 2022 with L5 nerve root (NR) compression and, along their clinical courses, concomitant compression of the common peroneal nerve (CPN) at the fibular head were included. Information on clinical features, diagnostics and surgeries was obtained. The outcome was assessed at the last outpatient follow-up appointment. In addition, an extensive literature review has been conducted. Results: Fourteen patients were included with a mean follow-up of 6.8 months. The majority had pain (71%) or motor deficits (71%). Seven patients were referred for clinical and radiological L5 NR compression but were also found to have CPN compression; the other seven patients had persisting or recurrent symptoms after surgically or conservatively treated L5 NR compression, suggestive of additional peroneal neuropathy. All patients had CPN decompression at the fibular head, with successful results obtained in 93% of the patients. Pain of the lower leg improved in all patients, and dorsiflexion function improved in 78%. Conclusions: Concomitant L5 NR and CPN appear to occur more frequently than expected. Peroneal neuropathy can present simultaneously with L5 nerve radiculopathy or after surgically or conservatively treated L5 NR compression. Overlapping symptoms and variation in clinical presentations make it difficult to diagnose and, therefore, underrecognized. More awareness among treating physicians of this specific double crush syndrome is important to prevent any delay in treatment, in this case, a less invasive common peroneal nerve release at the fibular head, and to avoid unnecessary (additional) spinal surgery. Full article

Angioimmunoblastic T-cell lymphoma (AITL) is a rare and aggressive subtype of non-Hodgkin lymphoma, the monitoring of which is largely restricted to radiological methods. Diagnosis relies on identifying characteristic clinicopathological features, supported by the detection of recurrent somatic mutations in RHOA, TET2, IDH2 and DNMT3A. The characteristic molecular profile of AITL and the high levels of circulating tumour DNA (ctDNA) measurable in AITL before treatment makes this an attractive lymphoma subtype in which to further investigate the role of ctDNA monitoring. The detection of somatic mutations in pre-treatment AITL-containing tissue samples was compared to those detected in pre-treatment ctDNA samples in a cohort of 12 patients. Changes in ctDNA somatic mutation burden over time were then correlated with radiological response. All six paired pre-treatment ctDNA and tissue samples had variants in common. All (8/8) previously ctDNA-detectable IDH2 and RHOA variants were undetectable in ctDNA samples at the time of end-of-treatment complete metabolic response (CMR). In comparison, the majority of both previously ctDNA-detectable DNMT3A variants (3/4) and TET2 variants (6/11) were detectable in ctDNA samples at the time of end-of-treatment CMR. These observations suggest that IDH2/RHOA variants may be more reliable markers of measurable residual disease in AITL than DNMT3A/TET2 variants. Full article