Prospective implementation of AI-assisted screen reading to improve early detection of breast cancer.

Artificial intelligence (AI) has the potential to improve breast cancer screening; however, prospective evidence of the safe implementation of AI into real clinical practice is limited. A commercially available AI system was implemented as an additional reader to standard double reading to flag cases for further arbitration review among screened women. Performance was assessed prospectively in three phases: a single-center pilot rollout, a wider multicenter pilot rollout and a full live rollout. The results showed that, compared to double reading, implementing the AI-assisted additional-reader process could achieve 0.7-1.6 additional cancer detection per 1,000 cases, with 0.16-0.30% additional recalls, 0-0.23% unnecessary recalls and a 0.1-1.9% increase in positive predictive value (PPV) after 7-11% additional human reads of AI-flagged cases (equating to 4-6% additional overall reading workload). The majority of cancerous cases detected by the AI-assisted additional-reader process were invasive (83.3%) and small-sized (≤10 mm, 47.0%). This evaluation suggests that using AI as an additional reader can improve the early detection of breast cancer with relevant prognostic features, with minimal to no unnecessary recalls. Although the AI-assisted additional-reader workflow requires additional reads, the higher PPV suggests that it can increase screening effectiveness.

Comparing Prognostic Factors of Cancers Identified by Artificial Intelligence (AI) and Human Readers in Breast Cancer Screening.

Invasiveness status, histological grade, lymph node stage, and tumour size are important prognostic factors for breast cancer survival. This evaluation aims to compare these features for cancers detected by AI and human readers using digital mammography. Women diagnosed with breast cancer between 2009 and 2019 from three UK double-reading sites were included in this retrospective cohort evaluation. Differences in prognostic features of cancers detected by AI and the first human reader (R1) were assessed using chi-square tests, with significance at p < 0.05. From 1718 screen-detected cancers (SDCs) and 293 interval cancers (ICs), AI flagged 85.9% and 31.7%, respectively. R1 detected 90.8% of SDCs and 7.2% of ICs. Of the screen-detected cancers detected by the AI, 82.5% had an invasive component, compared to 81.1% for R1 (p-0.374). For the ICs, this was 91.5% and 93.8% for AI and R1, respectively (p = 0.829). For the invasive tumours, no differences were found for histological grade, tumour size, or lymph node stage. The AI detected more ICs. In summary, no differences in prognostic factors were found comparing SDC and ICs identified by AI or human readers. These findings support a potential role for AI in the double-reading workflow.

Improving shared decision making for lung cancer treatment by developing and validating an open-source web based patient decision aid for stage I-II non-small cell lung cancer.

The aim of this study was to develop and evaluate a proof-of-concept open-source individualized Patient Decision Aid (iPDA) with a group of patients, physicians, and computer scientists. The iPDA was developed based on the International Patient Decision Aid Standards (IPDAS). A previously published questionnaire was adapted and used to test the user-friendliness and content of the iPDA. The questionnaire contained 40 multiple-choice questions, and answers were given on a 5-point Likert Scale (1-5) ranging from "strongly disagree" to "strongly agree." In addition to the questionnaire, semi-structured interviews were conducted with patients. We performed a descriptive analysis of the responses. The iPDA was evaluated by 28 computer scientists, 21 physicians, and 13 patients. The results demonstrate that the iPDA was found valuable by 92% (patients), 96% (computer scientists), and 86% (physicians), while the treatment information was judged useful by 92%, 96%, and 95%, respectively. Additionally, the tool was thought to be motivating for patients to actively engage in their treatment by 92%, 93%, and 91% of the above respondents groups. More multimedia components and less text were suggested by the respondents as ways to improve the tool and user interface. In conclusion, we successfully developed and tested an iPDA for patients with stage I-II Non-Small Cell Lung Cancer (NSCLC).

Lessons From a Systematic Literature Search on Diagnostic DNA Methylation Biomarkers for Colorectal Cancer: How to Increase Research Value and Decrease Research Waste?

OBJECTIVES: To improve colorectal cancer (CRC) survival and lower incidence rates, colonoscopy and/or fecal immunochemical test screening are widely implemented. Although candidate DNA methylation biomarkers have been published to improve or complement the fecal immunochemical test, clinical translation is limited. We describe technical and methodological problems encountered after a systematic literature search and provide recommendations to increase (clinical) value and decrease research waste in biomarker research. In addition, we present current evidence for diagnostic CRC DNA methylation biomarkers. METHODS: A systematic literature search identified 331 diagnostic DNA methylation marker studies published before November 2020 in PubMed, EMBASE, Cochrane Library, and Google Scholar. For 136 bodily fluid studies, extended data extraction was performed. STARD criteria and level of evidence were registered to assess reporting quality and strength for clinical translation. RESULTS: Our systematic literature search revealed multiple issues that hamper the development of DNA methylation biomarkers for CRC diagnosis, including methodological and technical heterogeneity and lack of validation or clinical translation. For example, clinical translation and independent validation were limited, with 100 of 434 markers (23%) studied in bodily fluids, 3 of 434 markers (0.7%) translated into clinical tests, and independent validation for 92 of 411 tissue markers (22%) and 59 of 100 bodily fluids markers (59%). DISCUSSION: This systematic literature search revealed that major requirements to develop clinically relevant diagnostic CRC DNA methylation markers are often lacking. To avoid the resulting research waste, clinical needs, intended biomarker use, and independent validation should be better considered before study design. In addition, improved reporting quality would facilitate meta-analysis, thereby increasing the level of evidence and enabling clinical translation.

Stereotactic ablative body radiotherapy (SABR) combined with immunotherapy (L19-IL2) versus standard of care in stage IV NSCLC patients, ImmunoSABR: a multicentre, randomised controlled open-label phase II trial.

BACKGROUND: About 50% of non-small cell lung cancer (NSCLC) patients have metastatic disease at initial diagnosis, which limits their treatment options and, consequently, the 5-year survival rate (15%). Immune checkpoint inhibitors (ICI), either alone or in combination with chemotherapy, have become standard of care (SOC) for most good performance status patients. However, most patients will not obtain long-term benefit and new treatment strategies are therefore needed. We previously demonstrated clinical safety of the tumour-selective immunocytokine L19-IL2, consisting of the anti-ED-B scFv L19 antibody coupled to IL2, combined with stereotactic ablative radiotherapy (SABR). METHODS: This investigator-initiated, multicentric, randomised controlled open-label phase II clinical trial will test the hypothesis that the combination of SABR and L19-IL2 increases progression free survival (PFS) in patients with limited metastatic NSCLC. One hundred twenty-six patients will be stratified according to their metastatic load (oligo-metastatic: ≤5 or poly-metastatic: 6 to 10) and randomised to the experimental-arm (E-arm) or the control-arm (C-arm). The C-arm will receive SOC, according to the local protocol. E-arm oligo-metastatic patients will receive SABR to all lesions followed by L19-IL2 therapy; radiotherapy for poly-metastatic patients consists of irradiation of one (symptomatic) to a maximum of 5 lesions (including ICI in both arms if this is the SOC). The accrual period will be 2.5-years, starting after the first centre is initiated and active. Primary endpoint is PFS at 1.5-years based on blinded radiological review, and secondary endpoints are overall survival, toxicity, quality of life and abscopal response. Associative biomarker studies, immune monitoring, CT-based radiomics, stool collection, iRECIST and tumour growth rate will be performed. DISCUSSION: The combination of SABR with or without ICI and the immunocytokine L19-IL2 will be tested as 1st, 2nd or 3rd line treatment in stage IV NSCLC patients in 14 centres located in 6 countries. This bimodal and trimodal treatment approach is based on the direct cytotoxic effect of radiotherapy, the tumour selective immunocytokine L19-IL2, the abscopal effect observed distant from the irradiated metastatic site(s) and the memory effect. The first results are expected end 2023. TRIAL REGISTRATION: ImmunoSABR Protocol Code: NL67629.068.18; EudraCT: 2018-002583-11; Clinicaltrials.gov: NCT03705403; ISRCTN ID: ISRCTN49817477; Date of registration: 03-April-2019.

Radiomics: from qualitative to quantitative imaging.

Historically, medical imaging has been a qualitative or semi-quantitative modality. It is difficult to quantify what can be seen in an image, and to turn it into valuable predictive outcomes. As a result of advances in both computational hardware and machine learning algorithms, computers are making great strides in obtaining quantitative information from imaging and correlating it with outcomes. Radiomics, in its two forms "handcrafted and deep," is an emerging field that translates medical images into quantitative data to yield biological information and enable radiologic phenotypic profiling for diagnosis, theragnosis, decision support, and monitoring. Handcrafted radiomics is a multistage process in which features based on shape, pixel intensities, and texture are extracted from radiographs. Within this review, we describe the steps: starting with quantitative imaging data, how it can be extracted, how to correlate it with clinical and biological outcomes, resulting in models that can be used to make predictions, such as survival, or for detection and classification used in diagnostics. The application of deep learning, the second arm of radiomics, and its place in the radiomics workflow is discussed, along with its advantages and disadvantages. To better illustrate the technologies being used, we provide real-world clinical applications of radiomics in oncology, showcasing research on the applications of radiomics, as well as covering its limitations and its future direction.

Early body weight loss during concurrent chemo-radiotherapy for non-small cell lung cancer.

BACKGROUND AND PURPOSE: Radiation-esophagitis and weight loss are frequently observed toxicities in patients treated with concurrent chemo-radiotherapy (CT-RT) for non-small cell lung cancer (NSCLC) and might be related. The purpose was to investigate whether weight loss already starts early after initiation of CT-RT and precedes radiation-esophagitis. MATERIALS AND METHODS: In a retrospective cohort, weight and esophagitis grade ≥2 were assessed during the first weeks of (CT-)RT in patients treated with concurrent (n = 102) or sequential (n = 92) therapy. In a prospective validation study, data on body weight, esophagitis grade ≥2, nutritional intake and muscle strength were obtained before, during and following CT-RT. RESULTS: In the retrospective cohort, early weight loss was observed in concurrently treated patients (p = 0.002), independent of esophagitis ≥ grade 2. Early weight loss was also observed in the prospective cohort (p = 0.003) and was not accompanied by decreases in nutritional intake. In addition lower limb muscle strength rapidly declined (p = 0.042). In the later weeks of treatment, further body weight loss occurred (p < 0.001) despite increased nutritional supplementation and body weight was only partly recovered after 4 weeks post CT-RT (p = 0.003). CONCLUSIONS: Weight loss during concurrent CT-RT for NSCLC starts early and prior to onset of esophagitis, requiring timely and intense nutritional rehabilitation.

[¹8F]fluorodeoxyglucose uptake patterns in lung before radiotherapy identify areas more susceptible to radiation-induced lung toxicity in non-small-cell lung cancer patients.

PURPOSE: Our hypothesis was that pretreatment inflammation in the lung makes pulmonary tissue more susceptible to radiation damage. The relationship between pretreatment [(18)F]fluorodeoxyglucose ([(18)F]FDG) uptake in the lungs (as a surrogate for inflammation) and the delivered radiation dose and radiation-induced lung toxicity (RILT) was investigated. METHODS AND MATERIALS: We retrospectively studied a prospectively obtained cohort of 101 non-small-cell lung cancer patients treated with (chemo)radiation therapy (RT). [(18)F]FDG-positron emission tomography-computed tomography (PET-CT) scans used for treatment planning were studied. Different parameters were used to describe [(18)F]FDG uptake patterns in the lungs, excluding clinical target volumes, and the interaction with radiation dose. An increase in the dyspnea grade of 1 (Common Terminology Criteria for Adverse Events version 3.0) or more points compared to the pre-RT score was used as an endpoint for analysis of RILT. The effect of [(18)F]FDG and CT-based variables, dose, and other patient or treatment characteristics that effected RILT was studied using logistic regression. RESULTS: Increased lung density and pretreatment [(18)F]FDG uptake were related to RILT after RT with univariable logistic regression. The 95th percentile of the [(18)F]FDG uptake in the lungs remained significant in multivariable logistic regression (p = 0.016; odds ratio [OR] = 4.3), together with age (p = 0.029; OR = 1.06), and a pre-RT dyspnea score of ≥1 (p = 0.005; OR = 0.20). Significant interaction effects were demonstrated among the 80th, 90th, and 95th percentiles and the relative lung volume receiving more than 2 and 5 Gy. CONCLUSIONS: The risk of RILT increased with the 95th percentile of the [(18)F]FDG uptake in the lungs, excluding clinical tumor volume (OR = 4.3). The effect became more pronounced as the fraction of the 5%, 10%, and 20% highest standardized uptake value voxels that received more than 2 Gy to 5 Gy increased. Therefore, the risk of RILT may be decreased by applying sophisticated radiotherapy techniques to avoid areas in the lung with high [(18)F]FDG uptake.

The ESTRO Breur Lecture 2009. From population to voxel-based radiotherapy: exploiting intra-tumour and intra-organ heterogeneity for advanced treatment of non-small cell lung cancer.

Evidence is accumulating that radiotherapy of non-small cell lung cancer patients can be optimized by escalating the tumour dose until the normal tissue tolerances are met. To further improve the therapeutic ratio between tumour control probability and the risk of normal tissue complications, we firstly need to exploit inter patient variation. This variation arises, e.g. from differences in tumour shape and size, lung function and genetic factors. Secondly improvement is achieved by taking into account intra-tumour and intra-organ heterogeneity derived from molecular and functional imaging. Additional radiation dose must be delivered to those parts of the tumour that need it the most, e.g. because of increased radio-resistance or reduced therapeutic drug uptake, and away from regions inside the lung that are most prone to complication. As the delivery of these treatments plans is very sensitive for geometrical uncertainties, probabilistic treatment planning is needed to generate robust treatment plans. The administration of these complicated dose distributions requires a quality assurance procedure that can evaluate the treatment delivery and, if necessary, adapt the treatment plan during radiotherapy.