Computer-aided detection system for lung cancer in computed tomography scans: Review and future prospects

Firmino, Macedo; Morais, Antônio Higor Freire de; Mendoça, Roberto M; Dantas, Marcel Ribeiro; Hékis, Hélio Roberto; Valentim, Ricardo Alexsandro de Medeiros

doi:10.1186/1475-925x-13-41

Cited by 131 publications

(66 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Typical CAD systems for lung cancer have the following pipeline: image preprocessing, detection of cancerous nodule candidates, nodule candidate false positive reduction, malignancy prediction for each nodule candidate, and malignancy prediction for overall CT scan [15]. These pipelines have many phases, each of which is computationally expensive and requires well-labeled data during training.…”

Section: Methodsmentioning

confidence: 99%

Lung Cancer Detection and Classification with 3D Convolutional Neural Network (3D-CNN)

Alakwaa¹,

Nassef²,

Badr³

2017

ijacsa

183

100

View full text Add to dashboard Cite

Abstract-This paper demonstrates a computer-aided diagnosis (CAD) system for lung cancer classification of CT scans with unmarked nodules, a dataset from the Kaggle Data Science Bowl, 2017. Thresholding was used as an initial segmentation approach to segment out lung tissue from the rest of the CT scan. Thresholding produced the next best lung segmentation. The initial approach was to directly feed the segmented CT scans into 3D CNNs for classification, but this proved to be inadequate. Instead, a modified U-Net trained on LUNA16 data (CT scans with labeled nodules) was used to first detect nodule candidates in the Kaggle CT scans. The U-Net nodule detection produced many false positives, so regions of CTs with segmented lungs where the most likely nodule candidates were located as determined by the U-Net output were fed into 3D Convolutional Neural Networks (CNNs) to ultimately classify the CT scan as positive or negative for lung cancer. The 3D CNNs produced a test set Accuracy of 86.6%. The performance of our CAD system outperforms the current CAD systems in literature which have several training and testing phases that each requires a lot of labeled data, while our CAD system has only three major phases (segmentation, nodule candidate detection, and malignancy classification), allowing more efficient training and detection and more generalizability to other cancers.

show abstract

Section: Methodsmentioning

confidence: 99%

Lung Cancer Detection and Classification with 3D Convolutional Neural Network (3D-CNN)

Alakwaa¹,

Nassef²,

Badr³

2017

ijacsa

183

100

View full text Add to dashboard Cite

show abstract

“…However, the high number of images produced by multidetector CT scanners has an impact on the workload of radiologists, which can lead to overlook of a lesion or misinterpretation of the findings (inability to properly diagnose a tumor) (57).…”

Section: Factors Leading To Missed Lung Cancer On Chest Ctmentioning

confidence: 99%

Missed lung cancer: when, where, and why?

Ciello

Franchi²,

Contegiacomo³

et al. 2017

Diagn Interv Radiol

131

106

View full text Add to dashboard Cite

L ung cancer accounts for 1.59 million deaths per year worldwide (1). It has one of the poorest survival outcomes of all cancers, with over two-thirds of patients diagnosed at an advanced stage, when curative treatment is no longer feasible. Early diagnosis of lung cancer is the main goal to improve survival. Patients with non-small cell lung cancer (NSCLC) at an operable stage have higher survival rates than those presenting with metastatic disease, with five-year survival of 71%-77% for stage IA and 58% for stage IB (2).Initial identification of lung cancer in asymptomatic patients usually occurs on chest radiography or chest computed tomography (CT). When missed on imaging, lung cancer is inclined to progress from early-stage to advanced-stage disease, particularly if many years pass between radiologic exams (3), with potential medicolegal consequences.Legal actions involving malignancies of the bronchus or lung represent the sixth most common medicolegal issue, and among radiologists it is the second most common cause for litigation (4). About 90% of presumed mistakes in pulmonary tumor diagnosis occurred on chest radiography, only 5% on CT examinations, and the remaining 5% on other imaging studies (4).Awareness of the possible causes for overlooking a pulmonary lesion can help radiologists to reduce the occurrence of this eventuality. In this review, we analyze factors leading to a misdiagnosis of lung cancer mainly on chest radiography, and we discuss the impact of misdiagnosis on prognosis, its medicolegal implications, and methods to reduce the incidence of missed lung cancer. Finally, we briefly analyze the possible causes of errors on CT scans and potential aids. Factors leading to missed lung cancer on chest radiographyFormerly, different authors recognized the burden of missed lung cancer on radiography of the thorax. Indeed, early studies on the analysis of factors leading to overlooked lung lesions date back to the middle of last century. Despite extensive technological advancement, this issue is currently present and not much has changed since then. Factors that contribute to missed lung cancer on chest X-ray can be classified as deriving from observer error, tumor characteristics, and technical considerations. C H E S T I MAG I N G R E V I E W ABSTRACTMissed lung cancer is a source of concern among radiologists and an important medicolegal challenge. In 90% of the cases, errors in diagnosis of lung cancer occur on chest radiographs. It may be challenging for radiologists to distinguish a lung lesion from bones, pulmonary vessels, mediastinal structures, and other complex anatomical structures on chest radiographs. Nevertheless, lung cancer can also be overlooked on computed tomography (CT) scans, regardless of the context, either if a clinical or radiologic suspect exists or for other reasons. Awareness of the possible causes of overlooking a pulmonary lesion can give radiologists a chance to reduce the occurrence of this eventuality. Various factors contribute to a misdiagnosis of lung cancer ...

show abstract

“…Reviews of techniques to detect pulmonary nodules from CT images are not something new; several critical reviews have already been written on the subject, especially to identify the best techniques already developed at the time, and to compare the data; for example, Lee et al [19], Sukuzi [20], Eadie, Taylor and Gibson [21], El-Baz et al [22] and Firmino et al [23]. Lee et al [19], Eadie, Taylor and Gibson [21] analyzed techniques until 2010 and Sukuzi [20] and El-Baz et al [22] till June 2012.…”

Section: Introductionmentioning

confidence: 99%

“…Lee et al [19], Eadie, Taylor and Gibson [21] analyzed techniques until 2010 and Sukuzi [20] and El-Baz et al [22] till June 2012. More recently, Firmino et al [23] reviewed through tol August 2013.…”

Section: Introductionmentioning

confidence: 99%

Automatic 3D pulmonary nodule detection in CT images: A survey

Valente

Cortez

Neto

et al. 2016

Computer Methods and Programs in Biomedicine

202

View full text Add to dashboard Cite

This work presents a systematic review of techniques for the 3D automatic detection of pulmonary nodules in computerized-tomography (CT) images.Its main goals are to analyze the latest technology being used for the development of computational diagnostic tools to assist in the acquisition, storage and, mainly, processing and analysis of the biomedical data. Also, this work identifies the progress made, so far, evaluates the challenges to be overcome and provides an analysis of future prospects. As far as the authors know, this is the first time that a review is devoted exclusively to automated 3D techniques for the detection of pulmonary nodules from lung CT images, which makes this work of noteworthy value. The research covered the published works in the Web of Science, PubMed, Science Direct and IEEEXplore up to December 2014. Each work found that referred to automated 3D segmentation of the lungs was individually analyzed to identify its objective, methodology and results. Based on the analysis of the selected works, several studies were seen to be useful for the construction of medical diagnostic * Corresponding author. E-mail: tavares@fe.up.pt. 31, 2015 aid tools. However, there are certain aspects that still require attention such as increasing algorithm sensitivity, reducing the number of false positives, improving and optimizing the algorithm detection of different kinds of nodules with different sizes and shapes and, finally, the ability to integrate with the Electronic Medical Record Systems and Picture Archiving and Communication Systems. Based on this analysis, we can say that further research is needed to develop current techniques and that new algorithms are needed to overcome the identified drawbacks. Preprint submitted to Computer Methods and Programs in Biomedicine August

show abstract

Computer-aided detection system for lung cancer in computed tomography scans: Review and future prospects

Cited by 131 publications

References 61 publications

Lung Cancer Detection and Classification with 3D Convolutional Neural Network (3D-CNN)

Lung Cancer Detection and Classification with 3D Convolutional Neural Network (3D-CNN)

Missed lung cancer: when, where, and why?

Automatic 3D pulmonary nodule detection in CT images: A survey

Contact Info

Product

Resources

About