Validated machine learning tools to distinguish immune checkpoint inhibitor, radiotherapy, COVID-19 and other infective pneumonitis.

BACKGROUND: Pneumonitis is a well-described, potentially disabling, or fatal adverse effect associated with both immune checkpoint inhibitors (ICI) and thoracic radiotherapy. Accurate differentiation between checkpoint inhibitor pneumonitis (CIP) radiation pneumonitis (RP), and infective pneumonitis (IP) is crucial for swift, appropriate, and tailored management to achieve optimal patient outcomes. However, correct diagnosis is often challenging, owing to overlapping clinical presentations and radiological patterns. METHODS: In this multi-centre study of 455 patients, we used machine learning with radiomic features extracted from chest CT imaging to develop and validate five models to distinguish CIP and RP from COVID-19, non-COVID-19 infective pneumonitis, and each other. Model performance was compared to that of two radiologists. RESULTS: Models to distinguish RP from COVID-19, CIP from COVID-19 and CIP from non-COVID-19 IP out-performed radiologists (test set AUCs of 0.92 vs 0.8 and 0.8; 0.68 vs 0.43 and 0.4; 0.71 vs 0.55 and 0.63 respectively). Models to distinguish RP from non-COVID-19 IP and CIP from RP were not superior to radiologists but demonstrated modest performance, with test set AUCs of 0.81 and 0.8 respectively. The CIP vs RP model performed less well on patients with prior exposure to both ICI and radiotherapy (AUC 0.54), though the radiologists also had difficulty distinguishing this test cohort (AUC values 0.6 and 0.6). CONCLUSION: Our results demonstrate the potential utility of such tools as a second or concurrent reader to support oncologists, radiologists, and chest physicians in cases of diagnostic uncertainty. Further research is required for patients with exposure to both ICI and thoracic radiotherapy.

Contrast Clearance Analysis (CCA) to Assess Viable Tumour following Stereotactic Radiosurgery (SRS) to Brain Metastasis in Non-Small Cell Lung Cancer (NSCLC).

BACKGROUND AND OBJECTIVE: Brain metastases are common in lung cancer and increasingly treated using targeted radiotherapy techniques such as stereotactic radiosurgery (SRS). Using MRI, post-SRS changes may be difficult to distinguish from progressive brain metastasis. Contrast clearance analysis (CCA) uses T1-weighted MRI images to assess the clearance of gadolinium and can be thus used to assess vascularity and active tumours. DESIGN AND METHODS: We retrospectively assessed CCAs in 62 patients with non-small cell lung cancer (NSCLC) undergoing 104 CCA scans in a single centre. RESULTS: The initial CCA suggested the aetiology of equivocal changes on standard MRI in 80.6% of patients. In all patients whose initial CCA showed post-SRS changes and who underwent serial CCAs, the initial diagnosis was upheld with the serial imaging. In only two cases of a presumed progressive tumour on the initial CCA, subsequent treatment for radionecrosis was instigated; a retrospective review and re-evaluation of the CCAs show that progression was reported where a thin rim of rapid contrast clearance was seen, and this finding has been subsequently recognised as a feature of post-treatment change on CCAs. The lack of concordance with CCA findings in those who underwent surgical resection was also found to be due to the over-reporting of the thin blue rim as disease in the early cases of CCA use and, in three cases, potentially related to timelines longer than 7 days prior to surgery, both factors being unknown during the early implementation phase of CCA at our centre but subsequently learned. CONCLUSIONS: Our single-centre experience shows CCA to be feasible and useful in patients with NSCLC in cases of diagnostic uncertainty in MRI. It has helped guide treatment in the majority of patients, with subsequent outcomes following the implementation of the treatment based on the results, suggesting correct classification. Recommendations from our experience of the implementation include the careful consideration of the thin rim of the rapid contrast clearance and the timing of the CCA prior to surgery for suspected brain metastasis progression.

Outcomes of Patients Treated With RCHOP With a PET-Adapted Approach for Consolidative Radiotherapy: A Retrospective Single-Center Study at the Royal Marsden Hospital.

BACKGROUND: Treatment with CHOP-based chemotherapy with consolidative radiotherapy (CRT) for primary mediastinal B cell lymphoma (PMBCL) has been the standard approach in the pre-rituximab era. Overtreatment with CRT for patients who may have already been cured by primary immunochemotherapy in the rituximab era is a significant concern due to the long-term toxicity associated with radiotherapy. Positron emission tomography (PET) may help to identify patients who may not benefit from further CRT. METHODS: We conducted a retrospective review of patients treated at the Royal Marsden Hospital between 2003 and 2020 for PMBCL to assess CRT use and survival outcomes. RESULTS: Forty-three patients were identified, with 95% of the patients receiving R-CHOP. CRT was given in 5 patients. Five-year event-free survival was 79% (95% confidence interval: 64%-89%) and 5-year overall survival was 88% (95% confidence interval: 73%-95%). Seven of 9 patients with DS4 did not receive CRT and instead monitored with serial PET scans. None of these 7 patients relapsed in the mediastinum. CONCLUSION: CRT may be omitted in patients with a negative end of treatment PET scans; however, careful observation may also obviate the need for CRT in PET positive patients.

Oncological Outcomes After Multidisciplinary Management of Breast Implant-Associated Anaplastic Large Cell Lymphoma (BIA-ALCL).

INTRODUCTION: Breast implant-associated anaplastic large cell lymphoma (BIA-ALCL) is an uncommon type of non-Hodgkin lymphoma, associated with breast implant capsules. Despite improvements in our understanding of BIA-ALCL, communicating the prognosis to patients remains challenging due to limited long-term follow-up data. This has important implications for decision-making, including recommendations for subsequent reconstructive procedures. The aim of this study was to assess the longer-term oncological outcomes of patients receiving multidisciplinary treatment for BIA-ALCL. METHODS: This was a retrospective cohort study of BIA-ALCL patients treated at a tertiary referral unit. The data are presented using simple descriptive statistics. RESULTS: Between 2015 and 2022, 18 BIA-ALCL patients were treated at our institution. The median age at diagnosis was 48.5 (IQR 41-55) years. Ten patients developed BIA-ALCL after cosmetic breast augmentation, and 8 after breast reconstruction following mastectomy for cancer. All patients had a history of textured implant insertion. The median time from first implant surgery to diagnosis was 8.5 (IQR 7-12) years. All patients underwent en-bloc total capsulectomy with implant removal, and 2 received systemic therapy. Fifteen patients had Stage I (IA-IC) disease, 2 had Stage IIA and 1 Stage III BIA-ALCL, based on the TNM classification system. At a median follow-up of 45 (IQR 15-71) months, there were no episodes of local or systemic relapse or death. CONCLUSIONS: Surgical management for BIA-ALCL is sufficient in early-stage disease, and associated with excellent oncological outcomes. This information is reassuring for patients when discussing recurrence risk.

Incidentally detected 18 F-FDG PET-CT-avid thyroid nodules in patients with advanced malignancy: long-term oncological outcomes from a single-centre retrospective cohort.

OBJECTIVES: In this retrospective study, we assessed the clinical outcomes of patients with a primary malignancy who had incidentally detected thyroid avidity on their staging 18 F-fluorodeoxyglucose PET-computed tomography ( 18 F-FDG PET-CT) examinations. METHODS: A focused retrospective search was made using a Radiology Information System to identify only patients with positive thyroid nodules on their 18 F-FDG PET-CT imaging between January 2012 and December 2017. Patient demographics, principal oncological diagnosis, and stage were recorded. The sonographic appearances of thyroid nodules, number of fine needle aspiration (FNA) attempts, final cytology, management plan, and clinical outcome were recorded. Follow-up records were available for between 2 and 7 years. RESULTS: Following exclusions, 136 patients were found to have incidental thyroid avidity on their 18 F-FDG PET-CT. A total of 50 of these patients proceeded to thyroid ultrasound assessment. Of these, 37 patients underwent FNA (average 1.3 FNA attempts) with 17 having atypical cytology and 6 diagnosed with an incidental thyroid cancer either by FNA or thyroidectomy. Four patients who underwent surgery had benign pathology. All thyroid cancers identified were indolent papillary cancers without any impact on the treatment plan or survival. CONCLUSION: The clinical outcomes of patients with an established primary malignancy are determined by their primary cancer and not by incidentally detected thyroid cancer. It may therefore be reasonable not to formally investigate a proportion of incidental 18 F-FDG PET-CT positive thyroid nodules where added benefit is unlikely. In such cases, a 'watch-and-wait' approach to the thyroid might be considered more appropriate.

Non-contrast CT synthesis using patch-based cycle-consistent generative adversarial network (Cycle-GAN) for radiomics and deep learning in the era of COVID-19.

Handcrafted and deep learning (DL) radiomics are popular techniques used to develop computed tomography (CT) imaging-based artificial intelligence models for COVID-19 research. However, contrast heterogeneity from real-world datasets may impair model performance. Contrast-homogenous datasets present a potential solution. We developed a 3D patch-based cycle-consistent generative adversarial network (cycle-GAN) to synthesize non-contrast images from contrast CTs, as a data homogenization tool. We used a multi-centre dataset of 2078 scans from 1,650 patients with COVID-19. Few studies have previously evaluated GAN-generated images with handcrafted radiomics, DL and human assessment tasks. We evaluated the performance of our cycle-GAN with these three approaches. In a modified Turing-test, human experts identified synthetic vs acquired images, with a false positive rate of 67% and Fleiss' Kappa 0.06, attesting to the photorealism of the synthetic images. However, on testing performance of machine learning classifiers with radiomic features, performance decreased with use of synthetic images. Marked percentage difference was noted in feature values between pre- and post-GAN non-contrast images. With DL classification, deterioration in performance was observed with synthetic images. Our results show that whilst GANs can produce images sufficient to pass human assessment, caution is advised before GAN-synthesized images are used in medical imaging applications.

Imaging in metastatic breast cancer, CT, PET/CT, MRI, WB-DWI, CCA: review and new perspectives.

BACKGROUND: Breast cancer is the most frequent cancer in women and remains the second leading cause of death in Western countries. It represents a heterogeneous group of diseases with diverse tumoral behaviour, treatment responsiveness and prognosis. While major progress in diagnosis and treatment has resulted in a decline in breast cancer-related mortality, some patients will relapse and prognosis in this cohort of patients remains poor. Treatment is determined according to tumor subtype; primarily hormone receptor status and HER2 expression. Menopausal status and site of disease relapse are also important considerations in treatment protocols. MAIN BODY: Staging and repeated evaluation of patients with metastatic breast cancer are central to the accurate assessment of disease extent at diagnosis and during treatment; guiding ongoing clinical management. Advances have been made in the diagnostic and therapeutic fields, particularly with new targeted therapies. In parallel, oncological imaging has evolved exponentially with the development of functional and anatomical imaging techniques. Consistent, reproducible and validated methods of assessing response to therapy is critical in effectively managing patients with metastatic breast cancer. CONCLUSION: Major progress has been made in oncological imaging over the last few decades. Accurate disease assessment at diagnosis and during treatment is important in the management of metastatic breast cancer. CT (and BS if appropriate) is generally widely available, relatively cheap and sufficient in many cases. However, several additional imaging modalities are emerging and can be used as adjuncts, particularly in pregnancy or other diagnostically challenging cases. Nevertheless, no single imaging technique is without limitation. The authors have evaluated the vast array of imaging techniques - individual, combined parametric and multimodal - that are available or that are emerging in the management of metastatic breast cancer. This includes WB DW-MRI, CCA, novel PET breast cancer-epitope specific radiotracers and radiogenomics.

The lung cancers: staging and response, CT, 18F-FDG PET/CT, MRI, DWI: review and new perspectives.

Lung cancer is the most commonly diagnosed cancer and the leading cause of cancer deaths in both sexes combined. Recent years have seen major advances in the diagnostic and treatment options for patients with non-small-cell lung cancer (NSCLC), including the routine use of 2-deoxy-2[18F]-fluoro-D-glucose positron emission tomography/computed tomography (18F-FDG PET/CT) in staging and response evaluation, minimally invasive endoscopic biopsy, targeted radiotherapy, minimally invasive surgery, and molecular and immunotherapies. In this review, the central roles of CT and 18F-FDG PET/CT in staging and response in both NSCLC and malignant pleural mesothelioma (MPM) are critically assessed. The Tumour Node Metastases (TNM-8) staging systems for NSCLC and MPM are presented with critical appraisal of the strengths and pitfalls of imaging. Overviews of the Response Evaluation Criteria in Solid Tumours (RECIST 1.1) for NSCLC and the modified RECIST criteria for MPM are provided, together with discussion of the benefits and limitations of these anatomical-based tools. Metabolic response assessment (not evaluated by RECIST 1.1) will be explored. We introduce the Positron Emission Tomography Response Criteria in Solid Tumours (PERCIST 1.0) to include its advantages and challenges. The limitations of both anatomical and metabolic assessment criteria when applied to NSCLC treated with immunotherapy and the important concept of pseudoprogression are addressed with reference to immune RECIST (iRECIST). Separate consideration is given to the diagnosis and follow up of solitary pulmonary nodules with reference to the British Thoracic Society guidelines and Fleischner guidelines and use of the Brock (CT-based) and Herder (addition of 18F-FDG PET/CT) models for assessing malignant potential. We discuss how these models inform decisions by the multidisciplinary team, including referral of suspicious nodules for non-surgical management in patients unsuitable for surgery. We briefly outline current lung screening systems being used in the UK, Europe and North America. Emerging roles for MRI in lung cancer imaging are reviewed. The use of whole-body MRI in diagnosing and staging NSCLC is discussed with reference to the recent multicentre Streamline L trial. The potential use of diffusion-weighted MRI to distinguish tumour from radiotherapy-induced lung toxicity is discussed. We briefly summarise the new PET-CT radiotracers being developed to evaluate specific aspects of cancer biology, other than glucose uptake. Finally, we describe how CT, MRI and 18F-FDG PET/CT are moving from primarily diagnostic tools for lung cancer towards having utility in prognostication and personalised medicine with the agency of artificial intelligence.

PARP inhibition utilized in combination therapy with Olaparib-Temozolomide to achieve disease stabilization in a rare case of BRCA1-mutant, metastatic myxopapillary ependymoma.

Myxopapillary ependymoma (MPE) is a primary tumor of the central nervous system (CNS), characteristically an indolent malignancy involving the spinal conus medullaris, Filum terminale or cauda equina. We present a rare case of MPE, recurrent in the pelvic soft tissue with eventual pleural and intra-pulmonary metastasis. Refractory to repeated gross resection, adjuvant radiotherapy, platinum-based chemotherapy and temozolomide exploitation of mutant somatic BRCA1 status with the addition of a poly (ADP-ribose); polymerase inhibitor (PARPi) in a novel combination regimen with olaparib-temozolomide (OT) has achieved stable radiological disease after 10 cycles.

Does the addition of whole-body MRI to routine imaging influence real-world treatment decisions in metastatic breast cancer?

BACKGROUND: The assessment of metastatic breast cancer (MBC) can be limited with routine imaging such as computed tomography (CT) especially in bone-only or bone-predominant disease. This analysis investigates the effects of the use of WBMRI in addition to the use of routine CT, bone scintigraphy (BS) and fluorine-18-fluorodeoxyglucose positron emission tomography with computed tomography (FDG-PET/CT) on influencing systemic anti-cancer treatment (SACT) decisions in patients with known MBC. METHODS: MBC patients undergoing SACT who had WBMRI undertaken within 8 weeks of either a routine CT, BS or FDG-PET/CT were reviewed retrospectively. The clinical indications for undertaking the WBMRI examinations were recorded. Data on the extent and distribution of the disease were collected and discordance/concordance of disease status across the imaging modalities were compared. SACT decisions at each time point were also evaluated. RESULTS: There were 105 MBC patients with 148 WBMRI studies paired with CT, BS or FDG-PET/CT. 50 pairs (33.8%) showed differences in the extent of disease, with 44 pairs due to additional sites (AS) reported on WBMRI alone. 81 patients (Group 1) had one WBMRI paired with routine imaging due to a variety of indications, with clinical symptoms (such as bone pain) being the most common (24.7%). 24 patients (Group 2) had more than one WBMRI study paired with routine imaging comprising 67 pairs. 13/67 pairs (19.4%) showed discordance in assessments. 10/13 pairs had progressive disease (PD) reported on WBMRI alone. SACT change due to AS reported on WBMRI alone occurred in 21/23 pairs (91.3%) in Group 1. SACT change due to PD reported on WBMRI alone in Group 2 occurred in 6/14 pairs (42.9%). SACT change due to AS/PD in both groups occurred in 11/102 pairs (10.8%) with known invasive ductal carcinoma (IDC) and 13/28 pairs (46.4%) with invasive lobular carcinoma (ILC). CONCLUSIONS: The use of WBMRI in MBC led to earlier recognition of PD and SACT change compared with the other imaging modalities. A higher proportion of discordant response assessments and SACT changes were observed in ILC compared with IDC in our patient group, although larger-scale studies are required to investigate this further.

A review on the added value of whole-body MRI in metastatic lobular breast cancer.

Invasive lobular breast carcinomas (ILC) account for approximately 15% of breast cancer diagnoses. They can be difficult to diagnose both clinically and radiologically, due to their infiltrative growth pattern. The pattern of metastasis of ILC is unusual, with spread to the serosal surfaces (pleura and peritoneum), retroperitoneum and gastrointestinal (GI)/genitourinary (GU) tracts and a higher rate of leptomeningeal spread than IDC. Routine staging and response assessment with computed tomography (CT) can be undertaken quickly and measurements can be reproduced easily, but this is challenging with metastatic ILC as bone-only/bone-predominant patterns are frequently seen and assessment of the disease status is limited in these scenarios. Functional imaging such as whole-body MRI (WBMRI) allows the assessment of bone and soft tissue disease by providing functional information related to differences in cellular density between malignant and benign tissues. A number of recent studies have shown that WBMRI can detect additional sites of disease in metastatic breast cancer (MBC), resulting in a change in systemic anti-cancer therapy. Although WBMRI and fluorodeoxyglucose-positron-emission tomography-computed tomography (FDG-PET/CT) have a comparable performance in the assessment of MBC, WBMRI can be particularly valuable as a proportion of ILC are non-FDG-avid, resulting in the underestimation of the disease extent. In this review, we explore the added value of WBMRI in the evaluation of metastatic ILC and compare it with other imaging modalities such as CT and FDG-PET/CT. We also discuss the spectrum of WBMRI findings of the different metastatic sites of ILC with CT and FDG-PET/CT correlation. KEY POINTS: • ILC has an unusual pattern of spread compared to IDC, with metastases to the peritoneum, retroperitoneum and GI and GU tracts, but the bones and liver are the commonest sites. • WBMRI allows functional assessment of metastatic disease, particularly in bone-only and bone-predominant metastatic cancers such as ILC where evaluation with CT can be challenging and limited. • WBMRI can detect more sites of disease compared with CT, can reveal disease progression earlier and provides the opportunity to change ineffective systemic treatment sooner.

Cost and clinical benefit of imaging surveillance after treatment for breast implant-associated anaplastic large cell lymphoma (BIA-ALCL).

Recent UK guidelines recommend that surveillance imaging should not be offered to patients who have undergone treatment for breast implant-associated anaplastic large cell lymphoma (BIA-ALCL) unless clinically indicated. The aim of this study was to explore the evolving practice at a tertiary referral unit and quantify the direct economic costs (DEC) associated with post-treatment BIA-ALCL routine radiological surveillance prior to adoption of the guidelines. Eleven patients were treated for BIA-ALCL between 2015 and 2020. At a median follow-up of 38 months (IQR 12-47) there were no local or distant relapses. Two patients did not have any radiological surveillance and 1 had follow-up elsewhere. The remaining 8 patients had a combination of positron emission tomography/computed tomography (PET/CT) (n = 10), CT (n = 2), breast ultrasound (n = 6), mammogram (n = 4) and breast magnetic resonance imaging (MRI) (n = 1) as routine imaging follow-up not guided by clinical concerns. Total cost of imaging was £10,396 (€12,257) with a median cost of £1953 (€2304) per patient [IQR £526-2029 (€621-2394)]. This cost could have been saved based on current guidelines recommending no routine surveillance for asymptomatic patients.