Impact of ultra-low dose CT acquisition on semi-automated RECIST tool in the evaluation of malignant focal liver lesions

Performance and clinical applicability of machine learning in liver computed tomography imaging: a systematic review

OBJECTIVES

Machine learning (ML) for medical imaging is emerging for several organs and image modalities. Our objectives were to provide clinicians with an overview of this field by answering the following questions: (1) How is ML applied in liver computed tomography (CT) imaging? (2) How well do ML systems perform in liver CT imaging? (3) What are the clinical applications of ML in liver CT imaging?

METHODS

A systematic review was carried out according to the guidelines from the PRISMA-P statement. The search string focused on studies containing content relating to artificial intelligence, liver, and computed tomography.

RESULTS

One hundred ninety-one studies were included in the study. ML was applied to CT liver imaging by image analysis without clinicians' intervention in majority of studies while in newer studies the fusion of ML method with clinical intervention have been identified. Several were documented to perform very accurately on reliable but small data. Most models identified were deep learning-based, mainly using convolutional neural networks. Potentially many clinical applications of ML to CT liver imaging have been identified through our review including liver and its lesion segmentation and classification, segmentation of vascular structure inside the liver, fibrosis and cirrhosis staging, metastasis prediction, and evaluation of chemotherapy.

CONCLUSION

Several studies attempted to provide transparent result of the model. To make the model convenient for a clinical application, prospective clinical validation studies are in urgent call. Computer scientists and engineers should seek to cooperate with health professionals to ensure this.

KEY POINTS

• ML shows great potential for CT liver image tasks such as pixel-wise segmentation and classification of liver and liver lesions, fibrosis staging, metastasis prediction, and retrieval of relevant liver lesions from similar cases of other patients. • Despite presenting the result is not standardized, many studies have attempted to provide transparent results to interpret the machine learning method performance in the literature. • Prospective studies are in urgent call for clinical validation of ML method, preferably carried out by cooperation between clinicians and computer scientists.

Artificial intelligence in diagnostic and interventional radiology: Where are we now?

The emergence of massively parallel yet affordable computing devices has been a game changer for research in the field of artificial intelligence (AI). In addition, dramatic investment from the web giants has fostered the development of a high-quality software stack. Going forward, the combination of faster computers with dedicated software libraries and the widespread availability of data has opened the door to more flexibility in the design of AI models. Radiomics is a process used to discover new imaging biomarkers that has multiple applications in radiology and can be used in conjunction with AI. AI can be used throughout the various processes of diagnostic imaging, including data acquisition, reconstruction, analysis and reporting. Today, the concept of "AI-augmented" radiologists is preferred to the theory of the replacement of radiologists by AI in many indications. Current evidence bolsters the assumption that AI-assisted radiologists work better and faster. Interventional radiology becomes a data-rich specialty where the entire procedure is fully recorded in a standardized DICOM format and accessible via standard picture archiving and communication systems. No other interventional specialty can bolster such readiness. In this setting, interventional radiology could lead the development of AI-powered applications in the broader interventional community. This article provides an update on the current status of radiomics and AI research, analyzes upcoming challenges and also discusses the main applications in AI in interventional radiology to help radiologists better understand and criticize articles reporting AI in medical imaging.

Value and prognostic impact of a deep learning segmentation model of COVID-19 lung lesions on low-dose chest CT

Objectives

1) To develop a deep learning (DL) pipeline allowing quantification of COVID-19 pulmonary lesions on low-dose computed tomography (LDCT). 2) To assess the prognostic value of DL-driven lesion quantification.

Methods

This monocentric retrospective study included training and test datasets taken from 144 and 30 patients, respectively. The reference was the manual segmentation of 3 labels: normal lung, ground-glass opacity(GGO) and consolidation(Cons). Model performance was evaluated with technical metrics, disease volume and extent. Intra- and interobserver agreement were recorded. The prognostic value of DL-driven disease extent was assessed in 1621 distinct patients using C-statistics. The end point was a combined outcome defined as death, hospitalization>10 days, intensive care unit hospitalization or oxygen therapy.

Results

The Dice coefficients for lesion (GGO+Cons) segmentations were 0.75±0.08, exceeding the values for human interobserver (0.70±0.08; 0.70±0.10) and intraobserver measures (0.72±0.09). DL-driven lesion quantification had a stronger correlation with the reference than inter- or intraobserver measures. After stepwise selection and adjustment for clinical characteristics, quantification significantly increased the prognostic accuracy of the model (0.82 vs. 0.90; p<0.0001).

Conclusions

A DL-driven model can provide reproducible and accurate segmentation of COVID-19 lesions on LDCT. Automatic lesion quantification has independent prognostic value for the identification of high-risk patients.

CT texture analysis as a predictor of favorable response to anti-PD1 monoclonal antibodies in metastatic skin melanoma

PURPOSE

The purpose of this study was to determine whether texture analysis features on pretreatment contrast-enhanced computed tomography (CT) images and their evolution can predict treatment response of metastatic skin melanoma (SM) treated with anti-PD1 monoclonal antibodies.

MATERIALS AND METHODS

Sixty patients (29 men, 31 women; median age, 56 years; age range: 27-91 years) with metastatic SM treated with pembrolizumab (43/60; 72%) or nivolumab (17/60; 28%) were included. Texture analysis of SM metastases was performed on baseline and first post-treatment evaluation CT examinations. Mean gray-level, entropy, kurtosis, skewness, and standard deviation values were derived from the pixel distribution histogram before and after spatial filtration at different anatomic scales, ranging from fine to coarse. Lasso penalized Cox regression analyses were performed to identify independent variables associated with favorable response to treatment.

RESULTS

A total of 127 metastases were analyzed, with a median of two metastases per patient. Skewness at fine texture scale (spatial scale filtration [SSF] = 2; Hazard ratio [HR]: 3.51; 95% CI: 2.08-8.57; P = 0.010), skewness at medium texture scale (SSF = 3; HR: 0.56; 95% CI: 0.11-1.59; P = 0.014), variation of entropy at fine texture scale (SSF = 2; HR: 37.76; 95% CI: 3.48-496.22; P = 0.008) and LDH above the threshold of 248 UI/L (HR: 3.56; 95% CI: 1.78-21.35; P = 0.032] were independent predictors of response to treatment.

CONCLUSION

Pretreatment CT texture analysis-derived tumor skewness and variation of entropy between baseline and first control CT examination may be used as predictors of favorable response to anti-PD1 monoclonal antibodies in patients with metastatic SM.

Comparison of two deep learning image reconstruction algorithms in chest CT images: A task-based image quality assessment on phantom data

PURPOSE

The purpose of this study was to compare the effect of two deep learning image reconstruction (DLR) algorithms in chest computed tomography (CT) with different clinical indications.

MATERIAL AND METHODS

Acquisitions on image quality and anthropomorphic phantoms were performed at six dose levels (CTDI_vol: 10/7.5/5/2.5/1/0.5mGy) on two CT scanners equipped with two different DLR algorithms (TrueFidelity^TM and AiCE). Raw data were reconstructed using the filtered back-projection (FBP) and the lowest/intermediate/highest DLR levels (L-DLR/M-DLR/H-DLR) of each algorithm. Noise power spectrum, task-based transfer function (TTF) and detectability index (d') were computed: d' modelled detection of a soft tissue mediastinal nodule, ground-glass opacity, or high-contrast pulmonary lesion. Subjective image quality of anthropomorphic phantom images was analyzed by two radiologists.

RESULTS

For the L-DLR/M-DLR levels, the noise magnitude was lower with TrueFidelity^TM than with AiCE from 2.5 to 10 mGy. For H-DLR, noise magnitude was lower with AiCE . For L-DLR and M-DLR, the average NPS spatial frequency (f_av) values were greater for AiCE except for 0.5 mGy. For H-DLR levels, f_av was greater for TrueFidelity^TM than for AiCE. TTF_50% values were greater with AiCE for the air insert, and lower than TrueFidelity^TM for the polyethylene insert. From 2.5 to10 mGy, d' was greater for AiCE than for TrueFidelity^TM for H-DLR for all lesions, but similar for L-DLR and M-DLR. Image quality was rated clinically appropriate for all levels of both algorithms, for dose from 2.5 to 10 mGy, except for L-DLR of AiCE.

CONCLUSION

DLR algorithms reduce the image-noise and improve lesion detectability. Their operations and properties impacted both noise-texture and spatial resolution.

Diagnostic performance of ultra-low dose versus standard dose CT for non-traumatic abdominal emergencies

PURPOSE

The purpose of this study was to compare the diagnostic performance of ultra-low dose (ULD) to that of standard (STD) computed tomography (CT) for the diagnosis of non-traumatic abdominal emergencies using clinical follow-up as reference standard.

MATERIALS AND METHODS

All consecutive patients requiring emergency abdomen-pelvic CT examination from March 2017 to September 2017 were prospectively included. ULD and STD CTs were acquired after intravenous administration iodinated contrast medium (portal phase). CT acquisitions were performed at 125mAs for STD and 55mAs for ULD. Diagnostic performance was retrospectively evaluated on ULD and STD CTs using clinical follow-up as a reference diagnosis.

RESULTS

A total of 308 CT examinations from 308 patients (145 men; mean age 59.1±20.7 (SD) years; age range: 18-96 years) were included; among which 241/308 (78.2%) showed abnormal findings. The effective dose was significantly lower with the ULD protocol (1.55±1.03 [SD] mSv) than with the STD (3.67±2.56 [SD] mSv) (P<0.001). Sensitivity was significantly lower for the ULD protocol (85.5% [95%CI: 80.4-89.4]) than for the STD (93.4% [95%CI: 89.4-95.9], P<0.001) whereas specificities were similar (94.0% [95%CI: 85.1-98.0] vs. 95.5% [95%CI: 87.0-98.9], respectively). ULD sensitivity was equivalent to STD for bowel obstruction and colitis/diverticulitis (96.4% [95%CI: 87.0-99.6] and 86.5% [95%CI: 74.3-93.5] for ULD vs. 96.4% [95%CI: 87.0-99.6] and 88.5% [95%CI: 76.5-94.9] for STD, respectively) but lower for appendicitis, pyelonephritis, abscesses and renal colic (75.0% [95%CI: 57.6-86.9]; 77.3% [95%CI: 56.0-90.1]; 90.5% [95%CI: 69.6-98.4] and 85% [95%CI: 62.9-95.4] for ULD vs. 93.8% [95%CI: 78.6-99.2]; 95.5% [95%CI: 76.2-100.0]; 100.0% [95%CI: 81.4-100.0] and 100.0% [95%CI: 80.6-100.0] for STD, respectively). Sensitivities were significantly different between the two protocols only for appendicitis (P=0.041).

CONCLUSION

In an emergency context, for patients with non-traumatic abdominal emergencies, ULD-CT showed inferior diagnostic performance compared to STD-CT for most abdominal conditions except for bowel obstruction and colitis/diverticulitis detection.