Improving Lung Lesion Detection in Low Dose Positron Emission Tomography Images Using Machine Learning

Nai, Ying-Hwey; Schaefferkoetter, Joshua; Fakhry-Darian, Daniel; Conti, Maurizio; Shi, Xinmei; Townsend, David W.; Sinha, Arvind; Tham, Ivan; Alexander, Daniel C.; Reilhac, Anthonin

doi:10.1109/nssmic.2018.8824292

Cited by 9 publications

(5 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning can be used to improve the identification of lung lesions in low dose positron emission tomography images, according to Nai et al [18]. They investigate if it is feasible to enhance lesion diagnosis during low-dose PET scans by transforming low-dose PET pictures to normal dosage, high-quality images using machine learning.…”

Section: Literature Surveymentioning

confidence: 99%

Machine Learning-Based Lung Cancer Classification and Enhanced Accuracy on CT Images

Gaddala,

Radha,

Buraga

et al. 2024

View full text Add to dashboard Cite

Lung cancer ranks as one of the main sources of death around the world. Because of the absence of symptoms in beginning phase patients, identifying and evaluating affected areas presents a significant challenge. Consequently, the mortality rate associated with lung cancer surpasses that of other lung diseases. Cellular breakdown in the lungs can be ordered into three sorts as Non-Small Cell Lung Cancer (NSCLC), Small Cell Lung Cancer (SCLC), and Carcinoid. Early detection is imperative, as it enables individuals to live longer lives. Computed Tomography (CT) scans are employed to locate tumors and determine the extent of cancer spread within the body. Early conclusion and characterization of cellular breakdown in the lungs are vital for working on a patient's possibilities of endurance, necessitating prompt lung disease detection. Accordingly, numerous machine learning and image processing models have been developed. This work efficiently classifies lung cancer as benign, malignant, or normal using a machine learning-based method for improved accuracy in lung cancer diagnosis on CT scans. The suggested model's accuracy on CT scans is increased by using the Random Forest algorithm to the detection of lung cancer. Metrics for accuracy, precision, sensitivity, and recall are used to assess the effectiveness of the approach that is being given.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Machine Learning-Based Lung Cancer Classification and Enhanced Accuracy on CT Images

Gaddala,

Radha,

Buraga

et al. 2024

View full text Add to dashboard Cite

show abstract

“…This will allow for improved lesion detection using low-dose PET scans. In order to map parameters from low-quality images to high-quality images, an algorithm called image quality transfer (IQT), which is a machine learning algorithm that uses patch-regression is used [21].…”

Section: Reviews On Lung Image Classification Systemsmentioning

confidence: 99%

CT Lung Image Classification Systems - A Systematic Review

Prabhakar¹,

Sivasubramanian²,

Sundaram³

et al. 2023

View full text Add to dashboard Cite

Computer Aided Detection (CAD) and diagnostic technologies and their application have emerged in the last decade. CAD applications have concentrated on identification of the region of interest, for example nodules in the lung in the images, and analysis of the characteristics of objects. CAD technologies take advantages of computer systems as well as image processing and analysis techniques to overcome perceptual and interpretive errors caused by radiologists in the process of image observation and interpretation. This fact is inevitable in the context of medical practice since experience of image readers may vary and each observer (such as a radiologist) has a unique visual search on an image. Furthermore, there are always inter and intra observer variability for interpretation of an image. To overcome these difficulties, different CAD systems are developed for medical image analysis. This paper presents a systematic review on different CAD systems for lung cancer classification using computed tomography images.

show abstract

“…Further, transfer learning has eased this process significantly through the usage of pretrained models that use a lesser number of images in retaining the learned information and detecting it with greater accuracy. Various researchers have used AI- and CNN-based techniques to find the presence of brain tumors [ 15 ], lesions [ 16 ], breast cancer [ 17 ], etc., as summarized in Table 1 . CNN is used on CT scans to identify the nature of the malignant pulmonary nodes [ 18 ], along with pneumonia via chest imaging scans [ 19 , 20 ].…”

Section: Related Workmentioning

confidence: 99%

Deep Learning-Aided Automated Pneumonia Detection and Classification Using CXR Scans

Jain

Singh

Saurabh

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The COVID-19 pandemic has caused a worldwide catastrophe and widespread devastation that reeled almost all countries. The pandemic has mounted pressure on the existing healthcare system and caused panic and desperation. The gold testing standard for COVID-19 detection, reverse transcription-polymerase chain reaction (RT-PCR), has shown its limitations with 70% accuracy, contributing to the incorrect diagnosis that exaggerated the complexities and increased the fatalities. The new variations further pose unseen challenges in terms of their diagnosis and subsequent treatment. The COVID-19 virus heavily impacts the lungs and fills the air sacs with fluid causing pneumonia. Thus, chest X-ray inspection is a viable option if the inspection detects COVID-19-induced pneumonia, hence confirming the exposure of COVID-19. Artificial intelligence and machine learning techniques are capable of examining chest X-rays in order to detect patterns that can confirm the presence of COVID-19-induced pneumonia. This research used CNN and deep learning techniques to detect COVID-19-induced pneumonia from chest X-rays. Transfer learning with fine-tuning ensures that the proposed work successfully classifies COVID-19-induced pneumonia, regular pneumonia, and normal conditions. Xception, Visual Geometry Group 16, and Visual Geometry Group 19 are used to realize transfer learning. The experimental results were promising in terms of precision, recall, F1 score, specificity, false omission rate, false negative rate, false positive rate, and false discovery rate with a COVID-19-induced pneumonia detection accuracy of 98%. Experimental results also revealed that the proposed work has not only correctly identified COVID-19 exposure but also made a distinction between COVID-19-induced pneumonia and regular pneumonia, as the latter is a very common disease, while COVID-19 is more lethal. These results mitigated the concern and overlap in the diagnosis of COVID-19-induced pneumonia and regular pneumonia. With further integrations, it can be employed as a potential standard model in differentiating the various lung-related infections, including COVID-19.

show abstract

Improving Lung Lesion Detection in Low Dose Positron Emission Tomography Images Using Machine Learning

Cited by 9 publications

References 2 publications

Machine Learning-Based Lung Cancer Classification and Enhanced Accuracy on CT Images

Machine Learning-Based Lung Cancer Classification and Enhanced Accuracy on CT Images

CT Lung Image Classification Systems - A Systematic Review

Deep Learning-Aided Automated Pneumonia Detection and Classification Using CXR Scans

Contact Info

Product

Resources

About