The Effects of Artificial Intelligence Assistance on the Radiologists’ Assessment of Lung Nodules on CT Scans: A Systematic Review

Ewals, Lotte J. S.; Borne, Ben E. E. M. van den; Jacobs, Igor

doi:10.3390/jcm12103536

Cited by 11 publications

(4 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various studies have compared the performance of AI algorithms versus radiologists and highlighted higher sensitivity and FP rate when AI is used as a concurrent or second reader [ 26 – 29 ]. AI algorithms were found to have a mean number of FPs/scan ranging from 0.09 to 3.8 and a mean sensitivity (on a nodule basis) ranging from 0.54 to 0.96 [ 28 ]. In a study by Li et al [ 30 ], it was shown that deep learning algorithms not derived only from the LIDC-IDRI dataset [ 31 ] achieved good performance in nodule detection when tested on an external dataset, with sensitivity ranging from 0.75 to 1.00.…”

Section: Discussionmentioning

confidence: 99%

Effect of emphysema on AI software and human reader performance in lung nodule detection from low-dose chest CT

Sourlos,

Pelgrim,

Wisselink

et al. 2024

Eur Radiol Exp

View full text Add to dashboard Cite

Background Emphysema influences the appearance of lung tissue in computed tomography (CT). We evaluated whether this affects lung nodule detection by artificial intelligence (AI) and human readers (HR). Methods Individuals were selected from the “Lifelines” cohort who had undergone low-dose chest CT. Nodules in individuals without emphysema were matched to similar-sized nodules in individuals with at least moderate emphysema. AI results for nodular findings of 30–100 mm3 and 101–300 mm3 were compared to those of HR; two expert radiologists blindly reviewed discrepancies. Sensitivity and false positives (FPs)/scan were compared for emphysema and non-emphysema groups. Results Thirty-nine participants with and 82 without emphysema were included (n = 121, aged 61 ± 8 years (mean ± standard deviation), 58/121 males (47.9%)). AI and HR detected 196 and 206 nodular findings, respectively, yielding 109 concordant nodules and 184 discrepancies, including 118 true nodules. For AI, sensitivity was 0.68 (95% confidence interval 0.57–0.77) in emphysema versus 0.71 (0.62–0.78) in non-emphysema, with FPs/scan 0.51 and 0.22, respectively (p = 0.028). For HR, sensitivity was 0.76 (0.65–0.84) and 0.80 (0.72–0.86), with FPs/scan of 0.15 and 0.27 (p = 0.230). Overall sensitivity was slightly higher for HR than for AI, but this difference disappeared after the exclusion of benign lymph nodes. FPs/scan were higher for AI in emphysema than in non-emphysema (p = 0.028), while FPs/scan for HR were higher than AI for 30–100 mm3 nodules in non-emphysema (p = 0.009). Conclusions AI resulted in more FPs/scan in emphysema compared to non-emphysema, a difference not observed for HR. Relevance statement In the creation of a benchmark dataset to validate AI software for lung nodule detection, the inclusion of emphysema cases is important due to the additional number of FPs. Key points • The sensitivity of nodule detection by AI was similar in emphysema and non-emphysema. • AI had more FPs/scan in emphysema compared to non-emphysema. • Sensitivity and FPs/scan by the human reader were comparable for emphysema and non-emphysema. • Emphysema and non-emphysema representation in benchmark dataset is important for validating AI. Graphical Abstract

show abstract

Section: Discussionmentioning

confidence: 99%

Effect of emphysema on AI software and human reader performance in lung nodule detection from low-dose chest CT

Sourlos,

Pelgrim,

Wisselink

et al. 2024

Eur Radiol Exp

View full text Add to dashboard Cite

show abstract

“…Leaving aside clinical considerations that contribute to the differential diagnosis of oral cancer and that the actual gold standard for tumor identification is the biopsy's histopathological analysis by a pathologist, it is important to highlight that AI holds great promise in this manner and is gaining weight in medical areas [52,53].…”

Section: Discussionmentioning

confidence: 99%

Artificial Intelligence for Image Analysis in Oral Squamous Cell Carcinoma: A Review

Pereira-Prado,

Martins-Silveira,

Sicco

et al. 2023

Diagnostics

View full text Add to dashboard Cite

Head and neck tumor differential diagnosis and prognosis have always been a challenge for oral pathologists due to their similarities and complexity. Artificial intelligence novel applications can function as an auxiliary tool for the objective interpretation of histomorphological digital slides. In this review, we present digital histopathological image analysis applications in oral squamous cell carcinoma. A literature search was performed in PubMed MEDLINE with the following keywords: “artificial intelligence” OR “deep learning” OR “machine learning” AND “oral squamous cell carcinoma”. Artificial intelligence has proven to be a helpful tool in histopathological image analysis of tumors and other lesions, even though it is necessary to continue researching in this area, mainly for clinical validation.

show abstract

“…Recent systematic reviews endorse AI assistance in lung nodule detection, exhibiting accuracy ranging from 82-98% and surpassing radiologists by 7% to 56%particularly in detecting small nodules and among younger radiologists. AI has also contributed to reducing false-positive rates within the last years [25][26][27].…”

Section: Imaging 1402 Artificial Intelligencementioning

confidence: 99%

ERS International Congress 2023: highlights from the Clinical Techniques, Imaging and Endoscopy Assembly

Moretti,

Pietersen,

Hassan

et al. 2023

ERJ Open Res

View full text Add to dashboard Cite

The Clinical Techniques, Imaging and Endoscopy Assembly is involved in the diagnosis and treatment of several pulmonary disease as demonstrated at the 2023 ERS International Congress in Milan (figure 1).From interventional pulmonology, the congress included several exciting results for the use of bronchoscopy in lung cancer including augmented fluoroscopy, robotic assisted bronchoscopy and cryobiopsies. In obstructive lung disease bronchoscopic treatment of emphysema with hyperinflation and chronic bronchitis were presented with the latest results. Research on use of cryobiopsies for the diagnosis of interstitial lung disease was further explored, aiming to elevate diagnostic yield and minimize risk.For imaging the latest updates in artificial intelligence is of great interest as a way to overcome the increased work-load for the radiologist. Novel imaging in sarcoidosis explored the use of MRI, photon counting CT and PET-CT in the diagnostic work-up. Lung cancer screening is still a hot topic and new results regarding incorporation of biomarkers, identifying knowledge gaps and improving the screening programs were presented.The use of ultrasound in respiratory medicine is an expanding field demonstrated by the large variety in studies presented at this year's congress. Ultrasound of the diaphragm in patients with ALS and myasthenia gravis was used to assess movements and predict respiratory fatigueness. Furthermore studies using ultrasound to diagnosis or monitor pulmonary disease were presented. The congress also included studies regarding the training and assessment of competencies as an important part of implementing ultrasound in clinical practice.

show abstract

The Effects of Artificial Intelligence Assistance on the Radiologists’ Assessment of Lung Nodules on CT Scans: A Systematic Review

Cited by 11 publications

References 40 publications

Effect of emphysema on AI software and human reader performance in lung nodule detection from low-dose chest CT

Effect of emphysema on AI software and human reader performance in lung nodule detection from low-dose chest CT

Artificial Intelligence for Image Analysis in Oral Squamous Cell Carcinoma: A Review

ERS International Congress 2023: highlights from the Clinical Techniques, Imaging and Endoscopy Assembly

Contact Info

Product

Resources

About