The Performance of Deep Learning Algorithms on Automatic Pulmonary Nodule Detection and Classification Tested on Different Datasets That Are Not Derived from LIDC-IDRI: A Systematic Review

Li, Dana; Vilmun, Bolette Mikela; Carlsen, Jonathan Frederik; Albrecht‐Beste, Elisabeth; Lauridsen, Carsten Ammitzbøl; Nielsen, Michael Bachmann; Hansen, Kristoffer Lindskov

doi:10.3390/diagnostics9040207

Cited by 45 publications

(32 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the past, a wide-array of techniques from feature-engineering approaches to deep learning techniques have been applied to nodule detection [ 18 ]. While feature-engineering techniques utilizing thresholding and edge detection struggled with FP/scans > 100, deep learning research has focused on optimizing recall at relatively lower FPs/scans values, ranging from 0.125 to 8 FPs/scan [ 11 , 19 , 20 ]. However, to the best of our knowledge, no prior approach has considered utilizing data commonly-found in radiology reports or emphasizing precision over recall.…”

Section: Discussionmentioning

confidence: 99%

“…There is a paucity of radiologic data with high quality labels for nodule detection, and lung nodules are no exception. One of the most popular datasets used to train and evaluate lung nodule detectors is LUNA, which contains only 888 CTs with 2290 nodules [ 11 , 19 , 20 ]. For comparison, the Common Objects in Context dataset is a benchmark dataset for everyday object detection tasks and contains over 200,000 images with over 1.5 million segmented objects [ 26 ].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

High precision localization of pulmonary nodules on chest CT utilizing axial slice number labels

et al. 2021

View full text Add to dashboard Cite

Background Reidentification of prior nodules for temporal comparison is an important but time-consuming step in lung cancer screening. We develop and evaluate an automated nodule detector that utilizes the axial-slice number of nodules found in radiology reports to generate high precision nodule predictions. Methods 888 CTs from Lung Nodule Analysis were used to train a 2-dimensional (2D) object detection neural network. A pipeline of 2D object detection, 3D unsupervised clustering, false positive reduction, and axial-slice numbers were used to generate nodule candidates. 47 CTs from the National Lung Cancer Screening Trial (NLST) were used for model evaluation. Results Our nodule detector achieved a precision of 0.962 at a recall of 0.573 on the NLST test set for any nodule. When adjusting for unintended nodule predictions, we achieved a precision of 0.931 at a recall 0.561, which corresponds to 0.06 false positives per CT. Error analysis revealed better detection of nodules with soft tissue attenuation compared to ground glass and undeterminable attenuation. Nodule margins, size, location, and patient demographics did not differ between correct and incorrect predictions. Conclusions Utilization of axial-slice numbers from radiology reports allowed for development of a lung nodule detector with a low false positive rate compared to prior feature-engineering and machine learning approaches. This high precision nodule detector can reduce time spent on reidentification of prior nodules during lung cancer screening and can rapidly develop new institutional datasets to explore novel applications of computer vision in lung cancer imaging.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

High precision localization of pulmonary nodules on chest CT utilizing axial slice number labels

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Many reviews included data collected from electronic medical records, hospital information systems, or any databank that used individual patient data to create predictive models or evaluate collective patterns [12,13,[16][17][18][19][20][21][24][25][26][27]30,[33][34][35]37,38,40,[42][43][44][45]. Additionally, four reviews included primary studies based on imaging datasets and databanks, assessing different parameters of accuracy [15,29,31,36]. Other reviews focused on genetic databases [28,35], data from assisted reproductive technologies [30], or publicly available data [11,14,22,32].…”

Section: Data Sources and Purposes Of Included Studiesmentioning

confidence: 99%

“…Most of the studies assessed the effects of big data analytics on noncommunicable diseases [12][13][14][15]17,21,22,24,27,31,32,34,36,38,[40][41][42][43][44]. Furthermore, three reviews covered mental health, associated with the indicator "suicide mortality rate" [19,25,45]; three studies were related to the indicator "probability of dying from any of cardiovascular, cancer, diabetes, or chronic renal disease" [16,18,20,28,29]; and two studies were related to the indicator "proportion of bloodstream infections due to antimicrobial-resistant organisms" [26,33].…”

Section: Who Indicators and Core Prioritiesmentioning

confidence: 99%

Impact of Big Data Analytics on People’s Health: Overview of Systematic Reviews and Recommendations for Future Studies

Nascimento¹,

Marcolino²,

Abdulazeem³

et al. 2021

J Med Internet Res

View full text Add to dashboard Cite

Background Although the potential of big data analytics for health care is well recognized, evidence is lacking on its effects on public health. Objective The aim of this study was to assess the impact of the use of big data analytics on people’s health based on the health indicators and core priorities in the World Health Organization (WHO) General Programme of Work 2019/2023 and the European Programme of Work (EPW), approved and adopted by its Member States, in addition to SARS-CoV-2–related studies. Furthermore, we sought to identify the most relevant challenges and opportunities of these tools with respect to people’s health. Methods Six databases (MEDLINE, Embase, Cochrane Database of Systematic Reviews via Cochrane Library, Web of Science, Scopus, and Epistemonikos) were searched from the inception date to September 21, 2020. Systematic reviews assessing the effects of big data analytics on health indicators were included. Two authors independently performed screening, selection, data extraction, and quality assessment using the AMSTAR-2 (A Measurement Tool to Assess Systematic Reviews 2) checklist. Results The literature search initially yielded 185 records, 35 of which met the inclusion criteria, involving more than 5,000,000 patients. Most of the included studies used patient data collected from electronic health records, hospital information systems, private patient databases, and imaging datasets, and involved the use of big data analytics for noncommunicable diseases. “Probability of dying from any of cardiovascular, cancer, diabetes or chronic renal disease” and “suicide mortality rate” were the most commonly assessed health indicators and core priorities within the WHO General Programme of Work 2019/2023 and the EPW 2020/2025. Big data analytics have shown moderate to high accuracy for the diagnosis and prediction of complications of diabetes mellitus as well as for the diagnosis and classification of mental disorders; prediction of suicide attempts and behaviors; and the diagnosis, treatment, and prediction of important clinical outcomes of several chronic diseases. Confidence in the results was rated as “critically low” for 25 reviews, as “low” for 7 reviews, and as “moderate” for 3 reviews. The most frequently identified challenges were establishment of a well-designed and structured data source, and a secure, transparent, and standardized database for patient data. Conclusions Although the overall quality of included studies was limited, big data analytics has shown moderate to high accuracy for the diagnosis of certain diseases, improvement in managing chronic diseases, and support for prompt and real-time analyses of large sets of varied input data to diagnose and predict disease outcomes. Trial Registration International Prospective Register of Systematic Reviews (PROSPERO) CRD42020214048; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=214048

show abstract

“…In einer neuen Übersichtsarbeit wurden Algorithmen überprüft, die nicht am Standard-LIDC-IDRI-Datensatz trainiert wurden [51]. In den 26 ausgewerteten Studien ermittelten die Autoren eine Genauigkeit von über 90 %.…”

Section: Datensätze Zum Maschinellen Lernenunclassified

Expertentreffen COPD: Technologische Innovationen in der Pneumologie – Facetten aus Diagnostik und Therapie

et al. 2020

View full text Add to dashboard Cite

ZusammenfassungEin wesentlicher Anteil der aktuellen technologischen Entwicklungen in der Pneumologie liegt in den verschiedenen Bereichen der Informationstechnologie. Das Spektrum reicht dabei von Smartphone-Apps, die im täglichen Leben oder der Praxis von Patienten oder Ärzten angewandt werden sollen, bis hin zum Einsatz der künstlichen Intelligenz in der Früherkennung. Die Diagnose-Genauigkeit von Apps zur Symptomanalyse ist dabei zurzeit noch sehr limitiert. Forschungsprojekte beschäftigen sich mit der Integration von Symptomen und Funktionsparametern in der Früherkennung, aber auch mit der Mobilitätserfassung als prognostischem Marker bei der COPD. Eine große Herausforderung stellt das Lungenkrebs-Screening mittels Computertomografie dar. Hier kann künstliche Intelligenz helfen, riesige Datenmengen zu bewältigen. Die Qualität hängt jedoch vom suffizienten Training der Systeme ab. Technologische Entwicklungen prägen alle Felder der Pneumologie. Sie erlauben in der diagnostischen und interventionellen Endoskopie die verbesserte Biopsietechnik und mikrostrukturelle Bildgebung. Methoden der Lungenfunktionsdiagnostik ermöglichen die differenzierte Analyse von atemmechanischen Störungen und können in die Beatmungstechnologie überführt werden. Die Translation von Grundlagenerkenntnissen zum Mikrobiom kann perspektivisch helfen, COPD-Exazerbationen besser zu verstehen und zielgerichteter zu behandeln.

show abstract

The Performance of Deep Learning Algorithms on Automatic Pulmonary Nodule Detection and Classification Tested on Different Datasets That Are Not Derived from LIDC-IDRI: A Systematic Review

Cited by 45 publications

References 53 publications

High precision localization of pulmonary nodules on chest CT utilizing axial slice number labels

High precision localization of pulmonary nodules on chest CT utilizing axial slice number labels

Impact of Big Data Analytics on People’s Health: Overview of Systematic Reviews and Recommendations for Future Studies

Expertentreffen COPD: Technologische Innovationen in der Pneumologie – Facetten aus Diagnostik und Therapie

Contact Info

Product

Resources

About