Radiation therapy with phenotypic medicine: towards N-of-1 personalization.

In current clinical practice, radiotherapy (RT) is prescribed as a pre-determined total dose divided over daily doses (fractions) given over several weeks. The treatment response is typically assessed months after the end of RT. However, the conventional one-dose-fits-all strategy may not achieve the desired outcome, owing to patient and tumor heterogeneity. Therefore, a treatment strategy that allows for RT dose personalization based on each individual response is preferred. Multiple strategies have been adopted to address this challenge. As an alternative to current known strategies, artificial intelligence (AI)-derived mechanism-independent small data phenotypic medicine (PM) platforms may be utilized for N-of-1 RT personalization. Unlike existing big data approaches, PM does not engage in model refining, training, and validation, and guides treatment by utilizing prospectively collected patient's own small datasets. With PM, clinicians may guide patients' RT dose recommendations using their responses in real-time and potentially avoid over-treatment in good responders and under-treatment in poor responders. In this paper, we discuss the potential of engaging PM to guide clinicians on upfront dose selections and ongoing adaptations during RT, as well as considerations and limitations for implementation. For practicing oncologists, clinical trialists, and researchers, PM can either be implemented as a standalone strategy or in complement with other existing RT personalizations. In addition, PM can either be used for monotherapeutic RT personalization, or in combination with other therapeutics (e.g. chemotherapy, targeted therapy). The potential of N-of-1 RT personalization with drugs will also be presented.

Is two-staged gamma knife surgery a reasonable management option for very large cerebellar metastases? A case series of three patients.

OBJECTIVE: Two-staged gamma knife surgery (GKS) is a method that may extend the upper tumor volume limit for using GKS in the management of brain metastases. However, the safety of treating very large posterior fossa lesions with this technique has not been well demonstrated. Therefore, we analyzed our experience in treating cerebellar metastases larger than 12 cm3 with two-staged GKS. METHODS: Four consecutive patients harboring 12 to 30 cm3 cerebellar metastases scheduled two-staged GKS were included in the study, and all but one patient completed the treatment. The treatment doses were 10-13 Gy. All patients were followed with regular MR imaging and clinical assessments, and the tumor volumes were measured on all treatment and follow-up images. RESULTS: Tumor progression was not demonstrated in any of the patients. Tumor volumes decreased by, on average, more than half between the two stages. The median survival was 22 months, and no patient died due to intracranial tumor progression. Peritumoral edema at the first GKS resolved in all patients, replaced by asymptomatic mild T2 changes in two of them not requiring any treatment. No radiation-induced complication has developed thus far. CONCLUSION: Staged GKS seems to be a feasible management option for very large cerebellar metastases.

Novel 3D printable PEEK-HA-Mg2SiO4 composite material for spine implants: biocompatibility and imaging compatibility assessments.

PURPOSE: To develop a novel 3D printable polyether ether ketone (PEEK)-hydroxyapatite (HA)-magnesium orthosilicate (Mg2SiO4) composite material with enhanced properties for potential use in tumour, osteoporosis and other spinal conditions. We aim to evaluate biocompatibility and imaging compatibility of the material. METHODS: Materials were prepared in three different compositions, namely composite A: 75 weight % PEEK, 20 weight % HA, 5 weight % Mg2SiO4; composite B: 70 weight% PEEK, 25 weight % HA, 5 weight % Mg2SiO4; and composite C: 65 weight % PEEK, 30 weight % HA, 5 weight % Mg2SiO4. The materials were processed to obtain 3D printable filament. Biomechanical properties were analysed as per ASTM standards and biocompatibility of the novel material was evaluated using indirect and direct cell cytotoxicity tests. Cell viability of the novel material was compared to PEEK and PEEK-HA materials. The novel material was used to 3D print a standard spine cage. Furthermore, the CT and MR imaging compatibility of the novel material cage vs PEEK and PEEK-HA cages were evaluated using a phantom setup. RESULTS: Composite A resulted in optimal material processing to obtain a 3D printable filament, while composite B and C resulted in non-optimal processing. Composite A enhanced cell viability up to ~ 20% compared to PEEK and PEEK-HA materials. Composite A cage generated minimal/no artefacts on CT and MR imaging and the images were comparable to that of PEEK and PEEK-HA cages. CONCLUSION: Composite A demonstrated superior bioactivity vs PEEK and PEEK-HA materials and comparable imaging compatibility vs PEEK and PEEK-HA. Therefore, our material displays an excellent potential to manufacture spine implants with enhanced mechanical and bioactive property.

Design and 3D printing of novel titanium spine rods with lower flexural modulus and stiffness profile with optimised imaging compatibility.

PURPOSE: To manufacture and test 3D printed novel design titanium spine rods with lower flexural modulus and stiffness compared to standard solid titanium rods for use in metastatic spine tumour surgery (MSTS) and osteoporosis. METHODS: Novel design titanium spine rods were designed and 3D printed. Three-point bending test was performed to assess mechanical performance of rods, while a French bender was used to assess intraoperative rod contourability. Furthermore, 3D printed spine rods were tested for CT & MR imaging compatibility using phantom setup. RESULTS: Different spine rod designs generated includes shell, voronoi, gyroid, diamond, weaire-phelan, kelvin, and star. Tests showed 3D printed rods had lower flexural modulus with reduction ranging from 2 to 25% versus standard rod. Shell rods exhibited highest reduction in flexural modulus of 25% (~ 77.4 GPa) and star rod exhibited lowest reduction in flexural modulus of 2% (100.8GPa). 3D printed rod showed reduction in stiffness ranging from 40 to 59%. Shell rod displayed highest reduction in stiffness of 59% (179.9 N/mm) and gyroid had least reduction in stiffness of 40% (~ 259.2 N/mm). Rod bending test showed that except gyroid, other rod designs demonstrated lesser bending difficulty versus standard rod. All 3D printed rods demonstrated improved CT/MR imaging compatibility with reduced artefacts versus standard rod. CONCLUSION: By utilising novel design approach, we successfully generated a spine rod design portfolio with lower flexural modulus/stiffness profile and better CT/MR imaging compatibility for potential use in MSTS/other conditions such as osteoporosis. Thus, exploration of new rod designs in surgical application could enhance treatment outcome and improve quality of life for patients.

A deep learning-based technique for the diagnosis of epidural spinal cord compression on thoracolumbar CT.

PURPOSE: To develop a deep learning (DL) model for epidural spinal cord compression (ESCC) on CT, which will aid earlier ESCC diagnosis for less experienced clinicians. METHODS: We retrospectively collected CT and MRI data from adult patients with suspected ESCC at a tertiary referral institute from 2007 till 2020. A total of 183 patients were used for training/validation of the DL model. A separate test set of 40 patients was used for DL model evaluation and comprised 60 staging CT and matched MRI scans performed with an interval of up to 2 months. DL model performance was compared to eight readers: one musculoskeletal radiologist, two body radiologists, one spine surgeon, and four trainee spine surgeons. Diagnostic performance was evaluated using inter-rater agreement, sensitivity, specificity and AUC. RESULTS: Overall, 3115 axial CT slices were assessed. The DL model showed high kappa of 0.872 for normal, low and high-grade ESCC (trichotomous), which was superior compared to a body radiologist (R4, κ = 0.667) and all four trainee spine surgeons (κ range = 0.625-0.838)(all p < 0.001). In addition, for dichotomous normal versus any grade of ESCC detection, the DL model showed high kappa (κ = 0.879), sensitivity (91.82), specificity (92.01) and AUC (0.919), with the latter AUC superior to all readers (AUC range = 0.732-0.859, all p < 0.001). CONCLUSION: A deep learning model for the objective assessment of ESCC on CT had comparable or superior performance to radiologists and spine surgeons. Earlier diagnosis of ESCC on CT could reduce treatment delays, which are associated with poor outcomes, increased costs, and reduced survival.

Incident Cardiovascular Diseases Among Survivors of High-Risk Stage II-III Colorectal Cancer: A Cluster-Wide Cohort Study.

BACKGROUND: The incidence and survival of colorectal cancer (CRC) are increasing. There is an increasing number of long-term survivors, many of whom are elderly and have comorbidities. We conducted a population-based study in Hong Kong to assess the long-term cardiovascular disease (CVD) incidence associated with adjuvant fluoropyrimidine-based chemotherapy among CRC survivors. PATIENTS AND METHODS: Using the population-based electronic medical database of Hong Kong, we identified adults who were diagnosed with high-risk stage II-III CRC and treated with radical surgery followed by adjuvant fluoropyrimidine-based chemotherapy between 2010 and 2019. We evaluated the cause-specific cumulative incidence of CVD (including ischemic heart disease, heart failure, cardiomyopathy, and stroke) using the flexible parametric competing risk modeling framework. The control group without a history of CVD was selected from among a noncancer random sample from primary care clinics in the same geographic area. RESULTS: We analyzed 1,037 treated patients with CRC and 5,078 noncancer controls. The adjusted cause-specific hazard ratio (HR) for CVD in the cancer cohort compared with the control group was 2.11 (95% CI, 1.39-3.20). The 1-, 5-, and 10-year cause-specific cumulative incidences were 2.0%, 4.5%, and 5.4% in the cancer cohort versus 1.2%, 3.0%, and 3.8% in the control group, respectively. Age at cancer diagnosis (HR per 5-year increase, 1.16; 95% CI, 1.08-1.24), male sex (HR, 1.40; 95% CI, 1.06-1.86), comorbidity (HR, 1.88; 95% CI, 1.36-2.61 for 1 comorbidity vs none, and HR, 6.61; 95% CI, 4.55-9.60 for ≥2 comorbidities vs none), diabetes (HR, 1.38; 95% CI, 1.04-1.84), hypertension (HR, 3.27; 95% CI, 2.39-4.50), and dyslipidemia/hyperlipidemia (HR, 2.53; 95% CI, 1.68-3.81) were associated with incident CVD. CONCLUSIONS: Exposure to adjuvant fluoropyrimidine-based chemotherapy was associated with an increased risk of CVD among survivors of high-risk stage II-III CRC. Cardiovascular risk monitoring of this group throughout cancer survivorship is advisable.

Clinical characteristics and genetic testing outcome of suspected hereditary peripheral nerve sheath tumours in a tertiary cancer institution in Singapore.

BACKGROUND: Peripheral Nerve Sheath Tumors (PNST) are a diverse group of mostly benign tumours uncommon in the general population. About 5-10% of PNSTs are hereditary, predominantly arising from germline variants in NF1, NF2, SMARCB1, or LZTR1 gene. METHODS: We reviewed the clinical characteristics and genetic testing results of patients referred to the NCIS Adult Cancer Genetics Clinic for suspected hereditary PNST. RESULTS: 3,001 patients suspected to have various hereditary cancer syndromes were evaluated between year 2000 to March 2021. 13 (0.4%) were clinically diagnosed to have hereditary PNSTs. The majority were male (54%), with a median age at presentation to the genetics clinic of 29 years (range 19-48). 11/13 (85%) patients had multiple PNSTs, 12/13 (92%) had young onset PNSTs, 5/13 (38.5%) had personal and family history of PNST. 11/13 patients (85%) had clinical features of neurofibromatosis type 1 (NF1) including one patient who also fulfilled clinical criteria of neurofibromatosis type 2 (NF2); 2/13 (14%) had multiple schwannomas. Four patients underwent multi-gene panel testing, including one patient with clinical NF1, one patient who met both clinical NF1 and NF2 criteria, and two patients with multiple schwannomas. The patient with clinical features of NF1 was heterozygous for a pathogenic c. 2033dup variant in the NF1 gene. The patient with both NF1/NF2 features was heterozygous for a novel c.732 T > A nonsense variant in the NF2 gene. The two patients with multiple schwannomas were heterozygous for a pathogenic/likely pathogenic variant in the LZTR1 gene and are the first LZTR1-positive schwannomatosis patients reported in Asia. CONCLUSION: Hereditary PNSTs are rare referrals to an adult cancer genetics clinic. NF1 is the most common PNST seen. LZTR1 variants may be the underlying cause in Asian patients with multiple schwannomatosis.

Readmission-Free Survival Analysis in Metastatic Spine Tumour Surgical Patients: A Novel Concept.

BACKGROUND: Outcomes commonly used to ascertain success of metastatic spine tumour surgery (MSTS) are 30-day complications/mortality and overall/disease-free survival. We believe a new, effective outcome indicator after MSTS would be the absence of unplanned hospital readmission (UHR) after index discharge. We introduce the concept of readmission-free survival (ReAFS), defined as 'the time duration between hospital discharge after index operation and first UHR or death'. The aim of this study is to identify factors influencing ReAFS in MSTS patients. PATIENTS AND METHODS: We retrospectively analysed 266 consecutive patients who underwent MSTS between 2005 and 2016. Demographics, oncological characteristics, procedural, preoperative and postoperative details were collected. ReAFS of patients within 2 years or until death was reviewed. Perioperative factors predictive of reduced ReAFS were evaluated using multivariate regression analysis. RESULTS: Of 266 patients, 230 met criteria for analysis. A total of 201 had UHR, whilst 1 in 8 (29/230) had no UHR. Multivariate analysis revealed that haemoglobin ≥ 12 g/dL, ECOG score of ≤ 2, primary prostate, breast and haematological cancers, comorbidities ≤ 3, absence of preoperative radiotherapy and shorter postoperative length of stay significantly prolonged the time to first UHR. CONCLUSIONS: Readmission-free survival is a novel concept in MSTS, which relies on patients' general condition, appropriateness of interventional procedures and underlying disease burden. Additionally, it may indicate the successful combination of a multi-disciplinary treatment approach. This information will allow oncologists and surgeons to identify patients who may benefit from increased surveillance following discharge to increase ReAFS. We envisage that ReAFS is a concept that can be extended to other surgical oncological fields.

Radiation Necrosis from Stereotactic Radiosurgery-How Do We Mitigate?

OPINION STATEMENT: Intracranial stereotactic radiosurgery (SRS) is an effective and convenient treatment for many brain conditions. Data regarding safety come mostly from retrospective single institutional studies and a small number of prospective studies. Variations in target delineation, treatment delivery, imaging follow-up protocols and dose prescription limit the interpretation of this data. There has been much clinical focus on radiation necrosis (RN) in particular, as it is being increasingly recognized on follow-up imaging. Symptomatic RN may be treated with medical therapy (such as corticosteroids and bevacizumab) with surgical resection being reserved for refractory patients. Nevertheless, RN remains a challenging condition to manage, and therefore upfront patient selection for SRS remains critical to provide complication-free control. Mitigation strategies need to be considered in situations where the baseline risk of RN is expected to be high-such as large target volume or re-irradiation. These may involve reduction in the prescribed dose or hypofractionated stereotactic radiation therapy (HSRT). Recently published guidelines and international meta-analysis report the benefit of HSRT in larger lesions, without compromising control rates. However, careful attention to planning parameters and SRS techniques still need to be adhered, even with HSRT. In cases where the risk is deemed to be high despite mitigation, a combination approach of surgery with or without post-operative radiation should be considered.

Is there an optimal timing between radiotherapy and surgery to reduce wound complications in metastatic spine disease? A systematic review.

PURPOSE: Surgery with radiation therapy (RT) is more effective in treating spinal metastases, than RT alone. However, RT when administered in close proximity to surgery may predispose to wound complications. There exist limited guidelines on the optimal timing between RT and surgery. The purpose of this systematic review is to: (1) address whether pre-operative RT (preop-RT) and/or post-operative RT (postop-RT) is associated with wound complications and (2) define the safe interval between RT and surgery or vice versa. METHODS: PubMed, Embase and Scopus databases were systematically searched for articles dealing with spinal metastases, treated with surgery and RT, and discussing wound status. RESULTS: We obtained 2332 articles from all databases, and after applying exclusion criteria, removing duplicates and reading the full text, we identified 27 relevant articles. Fourteen additional articles were identified by hand-search, leading to a total of 41 articles. All 41 mentioned wound complications/healing. Sixteen articles discussed preop-RT, 8 postop-RT, 15 both, and 2 mentioned intraoperative-RT with additional pre/postop-RT. Twenty studies mentioned surgery-RT time interval; one concluded that wound complications were higher when RT-surgery interval was ≤ 7 days. Seven studies reported significant association between preop-RT and wound complications. CONCLUSIONS: Evidence is insufficient to draw definitive conclusion about optimal RT-surgery interval. However, based on published literature and expert opinions, we conclude that an interval of 2 weeks, the minimum being 7 days, is optimum between RT-surgery or vice versa; this can be reduced further by postop-stereotactic body RT. If RT-surgery window is > 12 months, wound-complications rise. Postop-RT has fewer wound complications versus preop-RT.

Megavoltage Radiosensitization of Gold Nanoparticles on a Glioblastoma Cancer Cell Line Using a Clinical Platform.

Gold nanoparticles (GNPs) have demonstrated significant dose enhancement with kilovoltage (kV) X-rays; however, recent studies have shown inconsistent findings with megavoltage (MV) X-rays. We propose to evaluate the radiosensitization effect on U87 glioblastoma (GBM) cells in the presence of 42 nm GNPs and irradiated with a clinical 6 MV photon beam. Cytotoxicity and radiosensitization were measured using MTS and clonogenic cellular radiation sensitivity assays, respectively. The sensitization enhancement ratio was calculated for 2 Gy (SER2Gy) with GNP (100 µg/mL). Dark field and MTS assays revealed high co-localization and good biocompatibility of the GNPs with GBM cells. A significant sensitization enhancement of 1.45 (p = 0.001) was observed with GNP 100 µg/mL. Similarly, at 6 Gy, there was significant difference in the survival fraction between the GBM alone group (mean (M) = 0.26, standard deviation (SD) = 0.008) and the GBM plus GNP group (M = 0.07, SD = 0.05, p = 0.03). GNPs enabled radiosensitization in U87 GBM cells at 2 Gy when irradiated using a clinical platform. In addition to the potential clinical utility of GNPs, these studies demonstrate the effectiveness of a robust and easy to standardize an in-vitro model that can be employed for future studies involving metal nanoparticle plus irradiation.

Chemoradiotherapy versus chemoradiotherapy plus surgery for esophageal cancer.

BACKGROUND: Please see Appendix 4 for a glossary of terms.The outcome of patients with esophageal cancer is generally poor. Although multimodal therapy is standard, there is conflicting evidence regarding the addition of esophagectomy to chemoradiotherapy. OBJECTIVES: To compare the effectiveness and safety of chemoradiotherapy plus surgery with that of chemoradiotherapy alone in people with nonmetastatic esophageal carcinoma. SEARCH METHODS: We performed a computerized search for relevant studies, up to Feburary 2017, on the CENTRAL, MEDLINE, and Embase databases using MeSH headings and keywords. We searched five online databases of clinical trials, handsearched conference proceedings, and screened reference lists of retrieved papers. SELECTION CRITERIA: We included randomized controlled trials (RCTs) comparing chemoradiotherapy plus esophagectomy with chemoradiotherapy alone for localized esophageal carcinoma. We excluded RCTs comparing chemotherapy or radiotherapy alone with esophagectomy. DATA COLLECTION AND ANALYSIS: Two authors independently selected studies, extracted data, and assessed risk of bias and the quality of the evidence, using standardized Cochrane methodological procedures. The primary outcome was overall survival (OS), estimated with Hazard Ratio (HR). Secondary outcomes, estimated with risk ratio (RR), were local and distant progression-free survival (PFS), quality of life (QoL), treatment-related mortality and morbidity, and use of salvage procedures for dysphagia. Data were analyzed using a random effects model in Review Manager 5.3 software. MAIN RESULTS: From 2667 references, we identified two randomized studies, in six reports, that included 431 participants. All participants were clinically staged to have at least T3 and/or node positive thoracic esophageal carcinoma, 93% of which was squamous cell histology. The risk of methodological bias of the included studies was low to moderate.High-quality evidence found the addition of esophagectomy had little or no difference on overall survival (HR 0.99, 95% CI 0.79 to 1.24; P = 0.92; I² = 0%; two trials). Neither study reported PFS, therefore, freedom from loco-regional relapse was used as a proxy. Moderate-quality evidence suggested that the addition of esophagectomy probably improved freedom from locoregional relapse (HR 0.55, 95% CI 0.39 to 0.76; P = 0.0004; I² = 0%; two trials), but low-quality evidence suggested it may increase the risk of treatment-related mortality (RR 5.11, 95% CI 1.74 to 15.02; P = 0.003; I² = 2%; two trials).The other pre-specified outcomes (quality of life, treatment-related toxicity, and use of salvage procedures for dysphagia) were reported by only one study, which found very low-quality evidence that use of esophagectomy was associated with reduced short-term QoL (MD 0.93, 95% CI 0.24 to 1.62), and low-quality evidence that it reduced use of salvage procedures for dysphagia (HR 0.52, 95% CI 0.36 to 0.75). Neither study compared treatment-related morbidity between treatment groups. AUTHORS' CONCLUSIONS: Based on the available evidence, the addition of esophagectomy to chemoradiotherapy in locally advanced esophageal squamous cell carcinoma, provides little or no difference on overall survival, and may be associated with higher treatment-related mortality. The addition of esophagectomy probably delays locoregional relapse, however, this end point was not well defined in the included studies. It is undetermined whether these results can be applied to the treatment of adenocarcinomas, tumors involving the distal esophagus and gastro-esophageal junction, and to people with poor response to chemoradiation.

Accuracy of (18)F-flurodeoxyglucose-positron emission tomography/computed tomography in the staging of newly diagnosed nasopharyngeal carcinoma: a systematic review and meta-analysis.

BACKGROUND: The specific role of 18F-flurodeoxyglucose-positron emission tomography/computed tomography (FDG-PET/CT) in staging of nasopharyngeal carcinoma (NPC) remains to be validated. A systematic review and meta-analysis were performed to assess the accuracy of staging FDG-PET/CT for newly diagnosed NPC. METHODS: We searched various biomedical databases and conference proceedings for relevant studies. We determined the pooled sensitivities and specificities, diagnostic odds ratios (DOR) and constructed summary receiver operating characteristic (SROC) curves using the hierarchical regression model. RESULTS: 15 relevant studies including 851 patients were identified. Five addressed primary tumor (T), nine addressed regional lymph nodes (N) and seven addressed distant metastasis (M). The combined sensitivity estimate for FDG-PET/CT in T classification was 0.77 (95% confidence interval [CI] 0.59-0.95). For N classification, combined sensitivity was 0.84 (95% CI 0.76-0.91), specificity was 0.90 (95% CI 0.83-0.97), DOR was 82.4 (23.2-292.6) and Q*-index was 0.90. For M classification, the combined sensitivity estimate was 0.87 (95% CI 0.74-1.00), specificity was 0.98 (95% CI 0.96-1.00), DOR was 120.9 (43.0-340.0) and Q*-index was 0.89. CONCLUSION: FDG-PET/CT showed good accuracy in N and M but not T classification for newly diagnosed NPC. FDG-PET/CT, together with Magnetic resonance imaging (MRI) of the nasopharynx, should be part of the routine staging investigations.

Neoadjuvant short-course radiotherapy or chemoradiation plus consolidative chemotherapy followed by radical operation for locally advanced rectal cancer.

Introduction: Limited evidence compares short-course radiotherapy (SCRT) and long-course chemoradiotherapy (LCCRT), both of which are followed by consolidative chemotherapy before radical rectal surgery. We conducted a retrospective cohort study to assess treatment response, survival outcomes, and toxicity in patients with locally advanced rectal cancer. Materials and methods: Patients (cT3-4 and/or N+) treated with SCRT or LCCRT, consolidative chemotherapy, or total mesorectal excision between 2013 and 2021 were identified. the cause-specific cumulative incidence of disease-related treatment failure, locoregional recurrence, distant metastases, and overall survival were evaluated using flexible parametric competing risk analysis and Kaplan-Meier methods, adjusted for treatment regimens and clinicopathological factors. A pathological complete response (pCR), tumor downstaging, and toxicity have been reported. Results: Among the 144 patients, 115 (80%) underwent curative rectal surgery. The LCCRT and SCRT groups achieved pCR in 10 (18%) and seven (12%) patients, respectively (odds ratio, 1.68; 95% confidence interval [CI], 0.59-4.78). The adjusted cause-specific hazard ratio for disease-related treatment failure with LCCRT versus SCRT was 0.26 (95% CI, 0.08-0.87). Three-year cumulative probability of disease-related treatment failure was 10.0% and 25.6% for LCCRT and SCRT, respectively. No significant differences in T-downstaging, N-downstaging, significant pathologic downstaging (ypT0-2N0), locoregional failure, distant metastasis, or overall survival were found. Late rectal toxicity occurred in 10 (15%) LCCRT and two (3%) SCRT patients, respectively. Conclusion: LCCRT with consolidative chemotherapy demonstrated improved disease-related treatment failure compared with SCRT, despite higher late rectal toxicity. Further research is needed to assess the long-term oncologic outcomes and toxicity.

Application of Machine Learning for Differentiating Bone Malignancy on Imaging: A Systematic Review.

An accurate diagnosis of bone tumours on imaging is crucial for appropriate and successful treatment. The advent of Artificial intelligence (AI) and machine learning methods to characterize and assess bone tumours on various imaging modalities may assist in the diagnostic workflow. The purpose of this review article is to summarise the most recent evidence for AI techniques using imaging for differentiating benign from malignant lesions, the characterization of various malignant bone lesions, and their potential clinical application. A systematic search through electronic databases (PubMed, MEDLINE, Web of Science, and clinicaltrials.gov) was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A total of 34 articles were retrieved from the databases and the key findings were compiled and summarised. A total of 34 articles reported the use of AI techniques to distinguish between benign vs. malignant bone lesions, of which 12 (35.3%) focused on radiographs, 12 (35.3%) on MRI, 5 (14.7%) on CT and 5 (14.7%) on PET/CT. The overall reported accuracy, sensitivity, and specificity of AI in distinguishing between benign vs. malignant bone lesions ranges from 0.44-0.99, 0.63-1.00, and 0.73-0.96, respectively, with AUCs of 0.73-0.96. In conclusion, the use of AI to discriminate bone lesions on imaging has achieved a relatively good performance in various imaging modalities, with high sensitivity, specificity, and accuracy for distinguishing between benign vs. malignant lesions in several cohort studies. However, further research is necessary to test the clinical performance of these algorithms before they can be facilitated and integrated into routine clinical practice.

CURATE.AI COR-Tx platform as a digital therapy and digital diagnostic for cognitive function in patients with brain tumour postradiotherapy treatment: protocol for a prospective mixed-methods feasibility clinical trial.

INTRODUCTION: Conventional interventional modalities for preserving or improving cognitive function in patients with brain tumour undergoing radiotherapy usually involve pharmacological and/or cognitive rehabilitation therapy administered at fixed doses or intensities, often resulting in suboptimal or no response, due to the dynamically evolving patient state over the course of disease. The personalisation of interventions may result in more effective results for this population. We have developed the CURATE.AI COR-Tx platform, which combines a previously validated, artificial intelligence-derived personalised dosing technology with digital cognitive training. METHODS AND ANALYSIS: This is a prospective, single-centre, single-arm, mixed-methods feasibility clinical trial with the primary objective of testing the feasibility of the CURATE.AI COR-Tx platform intervention as both a digital intervention and digital diagnostic for cognitive function. Fifteen patient participants diagnosed with a brain tumour requiring radiotherapy will be recruited. Participants will undergo a remote, home-based 10-week personalised digital intervention using the CURATE.AI COR-Tx platform three times a week. Cognitive function will be assessed via a combined non-digital cognitive evaluation and a digital diagnostic session at five time points: preradiotherapy, preintervention and postintervention and 16-weeks and 32-weeks postintervention. Feasibility outcomes relating to acceptability, demand, implementation, practicality and limited efficacy testing as well as usability and user experience will be assessed at the end of the intervention through semistructured patient interviews and a study team focus group discussion at study completion. All outcomes will be analysed quantitatively and qualitatively. ETHICS AND DISSEMINATION: This study has been approved by the National Healthcare Group (NHG) DSRB (DSRB2020/00249). We will report our findings at scientific conferences and/or in peer-reviewed journals. TRIAL REGISTRATION NUMBER: NCT04848935.

Deep learning assessment compared to radiologist reporting for metastatic spinal cord compression on CT.

Introduction: Metastatic spinal cord compression (MSCC) is a disastrous complication of advanced malignancy. A deep learning (DL) algorithm for MSCC classification on CT could expedite timely diagnosis. In this study, we externally test a DL algorithm for MSCC classification on CT and compare with radiologist assessment. Methods: Retrospective collection of CT and corresponding MRI from patients with suspected MSCC was conducted from September 2007 to September 2020. Exclusion criteria were scans with instrumentation, no intravenous contrast, motion artefacts and non-thoracic coverage. Internal CT dataset split was 84% for training/validation and 16% for testing. An external test set was also utilised. Internal training/validation sets were labelled by radiologists with spine imaging specialization (6 and 11-years post-board certification) and were used to further develop a DL algorithm for MSCC classification. The spine imaging specialist (11-years expertise) labelled the test sets (reference standard). For evaluation of DL algorithm performance, internal and external test data were independently reviewed by four radiologists: two spine specialists (Rad1 and Rad2, 7 and 5-years post-board certification, respectively) and two oncological imaging specialists (Rad3 and Rad4, 3 and 5-years post-board certification, respectively). DL model performance was also compared against the CT report issued by the radiologist in a real clinical setting. Inter-rater agreement (Gwet's kappa) and sensitivity/specificity/AUCs were calculated. Results: Overall, 420 CT scans were evaluated (225 patients, mean age=60 ± 11.9[SD]); 354(84%) CTs for training/validation and 66(16%) CTs for internal testing. The DL algorithm showed high inter-rater agreement for three-class MSCC grading with kappas of 0.872 (p<0.001) and 0.844 (p<0.001) on internal and external testing, respectively. On internal testing DL algorithm inter-rater agreement (κ=0.872) was superior to Rad 2 (κ=0.795) and Rad 3 (κ=0.724) (both p<0.001). DL algorithm kappa of 0.844 on external testing was superior to Rad 3 (κ=0.721) (p<0.001). CT report classification of high-grade MSCC disease was poor with only slight inter-rater agreement (κ=0.027) and low sensitivity (44.0), relative to the DL algorithm with almost-perfect inter-rater agreement (κ=0.813) and high sensitivity (94.0) (p<0.001). Conclusion: Deep learning algorithm for metastatic spinal cord compression on CT showed superior performance to the CT report issued by experienced radiologists and could aid earlier diagnosis.

State-of-the-Art Imaging Techniques in Metastatic Spinal Cord Compression.

Metastatic Spinal Cord Compression (MSCC) is a debilitating complication in oncology patients. This narrative review discusses the strengths and limitations of various imaging modalities in diagnosing MSCC, the role of imaging in stereotactic body radiotherapy (SBRT) for MSCC treatment, and recent advances in deep learning (DL) tools for MSCC diagnosis. PubMed and Google Scholar databases were searched using targeted keywords. Studies were reviewed in consensus among the co-authors for their suitability before inclusion. MRI is the gold standard of imaging to diagnose MSCC with reported sensitivity and specificity of 93% and 97% respectively. CT Myelogram appears to have comparable sensitivity and specificity to contrast-enhanced MRI. Conventional CT has a lower diagnostic accuracy than MRI in MSCC diagnosis, but is helpful in emergent situations with limited access to MRI. Metal artifact reduction techniques for MRI and CT are continually being researched for patients with spinal implants. Imaging is crucial for SBRT treatment planning and three-dimensional positional verification of the treatment isocentre prior to SBRT delivery. Structural and functional MRI may be helpful in post-treatment surveillance. DL tools may improve detection of vertebral metastasis and reduce time to MSCC diagnosis. This enables earlier institution of definitive therapy for better outcomes.

Cytokine Release Syndrome in Cancer Patients Receiving Immune Checkpoint Inhibitors: A Case Series of 25 Patients and Review of the Literature.

Cytokine release syndrome (CRS) is a phenomenon of immune hyperactivation described in the setting of immunotherapy. Unlike other immune-related adverse events, CRS triggered by immune checkpoint inhibitors (ICIs) is not well described. The clinical characteristics and course of 25 patients with ICI-induced CRS from 2 tertiary hospitals were abstracted retrospectively from the medical records and analyzed. CRS events were confirmed by 2 independent reviewers and graded using the Lee et al. scale. The median duration of CRS was 15.0 days (Q1; Q3 6.3; 29.8) and 10 (40.0%) had multiple episodes of CRS flares. Comparing the clinical factors and biomarkers in Grades 1-2 and 3-5 CRS, we found that patients with Grades 3-5 CRS had following: (i) had longer time to fever onset [25.0 days (Q1; Q3 13.0; 136.5) vs. 3.0 days (Q1; Q3 0.0; 18.0), p=0.027]; (ii) more cardiovascular (p=0.002), neurologic (p=0.001), pulmonary (p=0.044) and rheumatic (p=0.037) involvement; (iii) lower platelet count (p=0.041) and higher urea (p=0.041) at presentation compared to patients with Grades 1-2 CRS. 7 patients (28.0%) with Grades 1-2 CRS were rechallenged using ICIs without event. 9 patients (36.0%) were treated with pulse methylprednisolone and 6 patients (24.0%) were treated with tocilizumab. Despite this, 3 patients (50%) who received tocilizumab had fatal (Grade 5) outcomes from ICI-induced CRS. Longer time to fever onset, lower platelet count and higher urea at presentation were associated with Grade 3-5 CRS. These parameters may be used to predict which patients are likely to develop severe CRS.