Significance of Image Reconstruction Parameters for Future Lung Cancer Risk Prediction Using Low-Dose Chest Computed Tomography and the Open-Access Sybil Algorithm.

PURPOSE: Sybil is a validated publicly available deep learning-based algorithm that can accurately predict lung cancer risk from a single low-dose computed tomography (LDCT) scan. We aimed to study the effect of image reconstruction parameters and CT scanner manufacturer on Sybil's performance. MATERIALS AND METHODS: Using LDCTs of a subset of the National Lung Screening Trial participants, which we previously used for internal validation of the Sybil algorithm (test set), we ran the Sybil algorithm on LDCT series pairs matched on kilovoltage peak, milliampere-seconds, reconstruction interval, reconstruction diameter, and either reconstruction filter or axial slice thickness. We also evaluated the cumulative effect of these parameters by combining the best- and the worst-performing parameters. A subanalysis compared Sybil's performance by CT manufacturer. We considered any LDCT positive if future lung cancer was subsequently confirmed by biopsy or surgical resection. The areas under the curve (AUCs) for each series pair were compared using DeLong's test. RESULTS: There was no difference in Sybil's performance between 1049 pairs of standard versus bone reconstruction filter (AUC at 1 year 0.84 [95% confidence interval (CI): 0.70-0.99] vs 0.86 [95% CI: 0.75-0.98], P = 0.87) and 1961 pairs of standard versus lung reconstruction filter (AUC at 1 year 0.98 [95% CI: 0.97-0.99] vs 0.98 [95% CI: 0.96-0.99], P = 0.81). Similarly, there was no difference in 1288 pairs comparing 2-mm versus 5-mm axial slice thickness (AUC at 1 year 0.98 [95% CI: 0.94-1.00] vs 0.99 [95% CI: 0.97-0.99], P = 0.68). The best-case scenario combining a lung reconstruction filter with 2-mm slice thickness compared with the worst-case scenario combining a bone reconstruction filter with 2.5-mm slice thickness uncovered a significantly different performance at years 2-4 (P = 0.03). Subanalysis showed no significant difference in performance between Siemens and Toshiba scanners. CONCLUSIONS: Sybil's predictive performance for future lung cancer risk is robust across different reconstruction filters and axial slice thicknesses, demonstrating its versatility in various imaging settings. Combining favorable reconstruction parameters can significantly enhance predictive ability at years 2-4. The absence of significant differences between Siemens and Toshiba scanners further supports Sybil's versatility.

Protein codes promote selective subcellular compartmentalization.

Cells have evolved mechanisms to distribute ~10 billion protein molecules to subcellular compartments where diverse proteins involved in shared functions must efficiently assemble. Here, we demonstrate that proteins with shared functions share amino acid sequence codes that guide them to compartment destinations. A protein language model, ProtGPS, was developed that predicts with high performance the compartment localization of human proteins excluded from the training set. ProtGPS successfully guided generation of novel protein sequences that selectively assemble in targeted subcellular compartments. ProtGPS also identified pathological mutations that change this code and lead to altered subcellular localization of proteins. Our results indicate that protein sequences contain not only a folding code, but also a previously unrecognized code governing their distribution in specific cellular compartments.

Distinct chemical environments in biomolecular condensates.

Diverse mechanisms have been described for selective enrichment of biomolecules in membrane-bound organelles, but less is known about mechanisms by which molecules are selectively incorporated into biomolecular assemblies such as condensates that lack surrounding membranes. The chemical environments within condensates may differ from those outside these bodies, and if these differed among various types of condensate, then the different solvation environments would provide a mechanism for selective distribution among these intracellular bodies. Here we use small molecule probes to show that different condensates have distinct chemical solvating properties and that selective partitioning of probes in condensates can be predicted with deep learning approaches. Our results demonstrate that different condensates harbor distinct chemical environments that influence the distribution of molecules, show that clues to condensate chemical grammar can be ascertained by machine learning and suggest approaches to facilitate development of small molecule therapeutics with optimal subcellular distribution and therapeutic benefit.

Artificial Intelligence and Machine Learning in Lung Cancer Screening.

Recent advances in artificial intelligence and machine learning (AI/ML) hold substantial promise to address some of the current challenges in lung cancer screening and improve health equity. This article reviews the status and future directions of AI/ML tools in the lung cancer screening workflow, focusing on determining screening eligibility, radiation dose reduction and image denoising for low-dose chest computed tomography (CT), lung nodule detection, lung nodule classification, and determining optimal screening intervals. AI/ML tools can assess for chronic diseases on CT, which creates opportunities to improve population health through opportunistic screening.

Role of sex in lung cancer risk prediction based on single low-dose chest computed tomography.

A validated open-source deep-learning algorithm called Sybil can accurately predict long-term lung cancer risk from a single low-dose chest computed tomography (LDCT). However, Sybil was trained on a majority-male cohort. Use of artificial intelligence algorithms trained on imbalanced cohorts may lead to inequitable outcomes in real-world settings. We aimed to study whether Sybil predicts lung cancer risk equally regardless of sex. We analyzed 10,573 LDCTs from 6127 consecutive lung cancer screening participants across a health system between 2015 and 2021. Sybil achieved AUCs of 0.89 (95% CI: 0.85-0.93) for females and 0.89 (95% CI: 0.85-0.94) for males at 1 year, p = 0.92. At 6 years, the AUC was 0.87 (95% CI: 0.83-0.93) for females and 0.79 (95% CI: 0.72-0.86) for males, p = 0.01. In conclusion, Sybil can accurately predict future lung cancer risk in females and males in a real-world setting and performs better in females than in males for predicting 6-year lung cancer risk.

Successful Development of a Natural Language Processing Algorithm for Pancreatic Neoplasms and Associated Histologic Features.

OBJECTIVES: Natural language processing (NLP) algorithms can interpret unstructured text for commonly used terms and phrases. Pancreatic pathologies are diverse and include benign and malignant entities with associated histologic features. Creating a pancreas NLP algorithm can aid in electronic health record coding as well as large database creation and curation. METHODS: Text-based pancreatic anatomic and cytopathologic reports for pancreatic cancer, pancreatic ductal adenocarcinoma, neuroendocrine tumor, intraductal papillary neoplasm, tumor dysplasia, and suspicious findings were collected. This dataset was split 80/20 for model training and development. A separate set was held out for testing purposes. We trained using convolutional neural network to predict each heading. RESULTS: Over 14,000 reports were obtained from the Mass General Brigham Healthcare System electronic record. Of these, 1252 reports were used for algorithm development. Final accuracy and F1 scores relative to the test set ranged from 95% and 98% for each queried pathology. To understand the dependence of our results to training set size, we also generated learning curves. Scoring metrics improved as more reports were submitted for training; however, some queries had high index performance. CONCLUSIONS: Natural language processing algorithms can be used for pancreatic pathologies. Increased training volume, nonoverlapping terminology, and conserved text structure improve NLP algorithm performance.

Sybil: A Validated Deep Learning Model to Predict Future Lung Cancer Risk From a Single Low-Dose Chest Computed Tomography.

PURPOSE: Low-dose computed tomography (LDCT) for lung cancer screening is effective, although most eligible people are not being screened. Tools that provide personalized future cancer risk assessment could focus approaches toward those most likely to benefit. We hypothesized that a deep learning model assessing the entire volumetric LDCT data could be built to predict individual risk without requiring additional demographic or clinical data. METHODS: We developed a model called Sybil using LDCTs from the National Lung Screening Trial (NLST). Sybil requires only one LDCT and does not require clinical data or radiologist annotations; it can run in real time in the background on a radiology reading station. Sybil was validated on three independent data sets: a heldout set of 6,282 LDCTs from NLST participants, 8,821 LDCTs from Massachusetts General Hospital (MGH), and 12,280 LDCTs from Chang Gung Memorial Hospital (CGMH, which included people with a range of smoking history including nonsmokers). RESULTS: Sybil achieved area under the receiver-operator curves for lung cancer prediction at 1 year of 0.92 (95% CI, 0.88 to 0.95) on NLST, 0.86 (95% CI, 0.82 to 0.90) on MGH, and 0.94 (95% CI, 0.91 to 1.00) on CGMH external validation sets. Concordance indices over 6 years were 0.75 (95% CI, 0.72 to 0.78), 0.81 (95% CI, 0.77 to 0.85), and 0.80 (95% CI, 0.75 to 0.86) for NLST, MGH, and CGMH, respectively. CONCLUSION: Sybil can accurately predict an individual's future lung cancer risk from a single LDCT scan to further enable personalized screening. Future study is required to understand Sybil's clinical applications. Our model and annotations are publicly available.[Media: see text].

Optimizing risk-based breast cancer screening policies with reinforcement learning.

Screening programs must balance the benefit of early detection with the cost of overscreening. Here, we introduce a novel reinforcement learning-based framework for personalized screening, Tempo, and demonstrate its efficacy in the context of breast cancer. We trained our risk-based screening policies on a large screening mammography dataset from Massachusetts General Hospital (MGH; USA) and validated this dataset in held-out patients from MGH and external datasets from Emory University (Emory; USA), Karolinska Institute (Karolinska; Sweden) and Chang Gung Memorial Hospital (CGMH; Taiwan). Across all test sets, we find that the Tempo policy combined with an image-based artificial intelligence (AI) risk model is significantly more efficient than current regimens used in clinical practice in terms of simulated early detection per screen frequency. Moreover, we show that the same Tempo policy can be easily adapted to a wide range of possible screening preferences, allowing clinicians to select their desired trade-off between early detection and screening costs without training new policies. Finally, we demonstrate that Tempo policies based on AI-based risk models outperform Tempo policies based on less accurate clinical risk models. Altogether, our results show that pairing AI-based risk models with agile AI-designed screening policies has the potential to improve screening programs by advancing early detection while reducing overscreening.

Multi-Institutional Validation of a Mammography-Based Breast Cancer Risk Model.

PURPOSE: Accurate risk assessment is essential for the success of population screening programs in breast cancer. Models with high sensitivity and specificity would enable programs to target more elaborate screening efforts to high-risk populations, while minimizing overtreatment for the rest. Artificial intelligence (AI)-based risk models have demonstrated a significant advance over risk models used today in clinical practice. However, the responsible deployment of novel AI requires careful validation across diverse populations. To this end, we validate our AI-based model, Mirai, across globally diverse screening populations. METHODS: We collected screening mammograms and pathology-confirmed breast cancer outcomes from Massachusetts General Hospital, USA; Novant, USA; Emory, USA; Maccabi-Assuta, Israel; Karolinska, Sweden; Chang Gung Memorial Hospital, Taiwan; and Barretos, Brazil. We evaluated Uno's concordance index for Mirai in predicting risk of breast cancer at one to five years from the mammogram. RESULTS: A total of 128,793 mammograms from 62,185 patients were collected across the seven sites, of which 3,815 were followed by a cancer diagnosis within 5 years. Mirai obtained concordance indices of 0.75 (95% CI, 0.72 to 0.78), 0.75 (95% CI, 0.70 to 0.80), 0.77 (95% CI, 0.75 to 0.79), 0.77 (95% CI, 0.73 to 0.81), 0.81 (95% CI, 0.79 to 0.82), 0.79 (95% CI, 0.76 to 0.83), and 0.84 (95% CI, 0.81 to 0.88) at Massachusetts General Hospital, Novant, Emory, Maccabi-Assuta, Karolinska, Chang Gung Memorial Hospital, and Barretos, respectively. CONCLUSION: Mirai, a mammography-based risk model, maintained its accuracy across globally diverse test sets from seven hospitals across five countries. This is the broadest validation to date of an AI-based breast cancer model and suggests that the technology can offer broad and equitable improvements in care.

Toward robust mammography-based models for breast cancer risk.

Improved breast cancer risk models enable targeted screening strategies that achieve earlier detection and less screening harm than existing guidelines. To bring deep learning risk models to clinical practice, we need to further refine their accuracy, validate them across diverse populations, and demonstrate their potential to improve clinical workflows. We developed Mirai, a mammography-based deep learning model designed to predict risk at multiple timepoints, leverage potentially missing risk factor information, and produce predictions that are consistent across mammography machines. Mirai was trained on a large dataset from Massachusetts General Hospital (MGH) in the United States and tested on held-out test sets from MGH, Karolinska University Hospital in Sweden, and Chang Gung Memorial Hospital (CGMH) in Taiwan, obtaining C-indices of 0.76 (95% confidence interval, 0.74 to 0.80), 0.81 (0.79 to 0.82), and 0.79 (0.79 to 0.83), respectively. Mirai obtained significantly higher 5-year ROC AUCs than the Tyrer-Cuzick model ( P < 0.001) and prior deep learning models Hybrid DL ( P < 0.001) and Image-Only DL ( P < 0.001), trained on the same dataset. Mirai more accurately identified high-risk patients than prior methods across all datasets. On the MGH test set, 41.5% (34.4 to 48.5) of patients who would develop cancer within 5 years were identified as high risk, compared with 36.1% (29.1 to 42.9) by Hybrid DL ( P = 0.02) and 22.9% (15.9 to 29.6) by the Tyrer-Cuzick model ( P < 0.001).

Ductal carcinoma in situ on digital mammography versus digital breast tomosynthesis: rates and predictors of pathologic upgrade.

OBJECTIVES: To compare upgrade rates of ductal carcinoma in situ (DCIS) on digital mammography (DM) versus digital breast tomosynthesis (DBT) and identify patient, imaging, and pathological features associated with upgrade risk. METHODS: A retrospective review was performed of 318 women (mean 59 years, range 37-89) with screening-detected DCIS from 2007 to 2011 (DM group) and from 2013 to 2016 (DBT group). Comparisons made between DM and DBT groups using the unpaired t test and chi-square test include detection rates of DCIS, upgrade rates to invasive cancer, and pathological features of DCIS and upgraded cases. Patient, imaging, and pathological features associated with upgrade were also determined. P values < 0.05 were considered significant. RESULTS: There was no significant difference in detection rates of DCIS between DM and DBT groups (0.9 versus 1.0 per 1000 examinations, p = 0.45). Upgrade rates of DCIS to invasive cancer in DM and DBT groups were similar (17.3% versus 16.8%, p = 0.90), despite significant differences in pathological features of DCIS between DM and DBT groups (including nuclear grade, comedonecrosis, and progesterone receptor status [p ≤ 0.01]). Among upgraded cases, a higher proportion were high-grade invasive cancers with DBT (36.7% versus 9.5%, p = 0.03). In both groups, ultrasound-guided (versus stereotactic) biopsy was associated with higher upgrade risk (p ≤ 0.03). CONCLUSIONS: There was no significant difference in detection rates or upgrade rates of DCIS on DM versus DBT; however, upgraded cases were more likely to be high grade with DBT, suggesting possible differences in tumor biology between cancers with DM and DBT. In both DM and DBT groups, biopsy modality was associated with upgrade risk. KEY POINTS: • Detection rates and upgrade rates of ductal carcinoma in situ (DCIS) on digital mammography (DM) versus digital breast tomosynthesis (DBT) are similar. • A higher proportion of upgraded cases were high-grade invasive cancers with DBT than DM, suggesting possible differences in tumor biology between cancers that are detected with DM and DBT. • With both DM and DBT, ultrasound-guided biopsy (versus stereotactic biopsy) was associated with a higher risk of upgrade.

Dietary methionine influences therapy in mouse cancer models and alters human metabolism.

Nutrition exerts considerable effects on health, and dietary interventions are commonly used to treat diseases of metabolic aetiology. Although cancer has a substantial metabolic component1, the principles that define whether nutrition may be used to influence outcomes of cancer are unclear2. Nevertheless, it is established that targeting metabolic pathways with pharmacological agents or radiation can sometimes lead to controlled therapeutic outcomes. By contrast, whether specific dietary interventions can influence the metabolic pathways that are targeted in standard cancer therapies is not known. Here we show that dietary restriction of the essential amino acid methionine-the reduction of which has anti-ageing and anti-obesogenic properties-influences cancer outcome, through controlled and reproducible changes to one-carbon metabolism. This pathway metabolizes methionine and is the target of a variety of cancer interventions that involve chemotherapy and radiation. Methionine restriction produced therapeutic responses in two patient-derived xenograft models of chemotherapy-resistant RAS-driven colorectal cancer, and in a mouse model of autochthonous soft-tissue sarcoma driven by a G12D mutation in KRAS and knockout of p53 (KrasG12D/+;Trp53-/-) that is resistant to radiation. Metabolomics revealed that the therapeutic mechanisms operate via tumour-cell-autonomous effects on flux through one-carbon metabolism that affects redox and nucleotide metabolism-and thus interact with the antimetabolite or radiation intervention. In a controlled and tolerated feeding study in humans, methionine restriction resulted in effects on systemic metabolism that were similar to those obtained in mice. These findings provide evidence that a targeted dietary manipulation can specifically affect tumour-cell metabolism to mediate broad aspects of cancer outcome.

Nutrient availability shapes methionine metabolism in p16/MTAP-deleted cells.

Codeletions of gene loci containing tumor suppressors and neighboring metabolic enzymes present an attractive synthetic dependency in cancers. However, the impact that these genetic events have on metabolic processes, which are also dependent on nutrient availability and other environmental factors, is unknown. As a proof of concept, we considered panels of cancer cells with homozygous codeletions in CDKN2a and MTAP, genes respectively encoding the commonly-deleted tumor suppressor p16 and an enzyme involved in methionine metabolism. A comparative metabolomics analysis revealed that while a metabolic signature of MTAP deletion is apparent, it is not preserved upon restriction of nutrients related to methionine metabolism. Furthermore, re-expression of MTAP exerts heterogeneous consequences on metabolism across isogenic cell pairs. Together, this study demonstrates that numerous factors, particularly nutrition, can overwhelm the effects of metabolic gene deletions on metabolism. These findings may also have relevance to drug development efforts aiming to target methionine metabolism.