Noting that overlapping imaging features on contrast-enhanced computed tomography (CT) can make it challenging to differentiate between acute diverticulitis and colon cancer, researchers say an emerging deep learning model may provide enhanced sensitivity and specificity for these conditions.

In a retrospective study recently published in 

, researchers developed and tested a three-dimensional (3D) convolutional neural network (CNN) for 585 patients (mean age of 63.2) who underwent surgery for colon cancer or acute diverticulitis between July 1, 2005 and October 1, 2020, had venous phase CT imaging within 60 days prior to surgery and had segmental wall thickening in the colon that was independent of disease stage.

In comparison to mean sensitivity and specificity rates of 77.6 percent and 81.6 percent, respectively, for radiologist readers, the study authors noted an 83.3 percent sensitivity rate and an 86.6 percent specificity rate for the 3D CNN model. The combination of the deep learning model and radiologist assessment resulted in an eight percent increase in sensitivity (85.6 percent) and a 9.7 percent increase in specificity (91.3 percent) over radiologist assessments, according to the study findings.

The study authors also noted the reduction of false-negative rates with the 3D CNN model. According to the study, the overall false-negative rate for radiology readers in the study decreased from 22 percent to 14.3 percent with adjunctive use of the 3D CNN algorithm. Specifically, the 3D CNN model led to a 4 percent reduction in false-negative rates (from 14 percent to 10 percent) for board-certified radiologists and a 9.9 percent reduction (from 26 percent to 16.1 percent) for radiology residents. 

The researchers said the reduction in false-negative findings has “major clinical implications” for patients with colon cancer or acute diverticulitis.

“In the perforated stage, both entities require emergency surgery; however, the surgical strategies differ. Whereas (colon cancer) requires oncologic resection of the diseased bowel and the entire lymph node basin, a limited resection of the diseased bowel may suffice in cases of (acute diverticulitis). A high level of certainty in surgical planning improves patient stratification and thus limits postoperative complications and potentially decreases mortality rates,” wrote study co-author Rickmer Braren, M.D., who is affiliated with the Institute of Diagnostic and Interventional Radiology at the School of Medicine at the Technical University of Munich in Germany, and colleagues.

(Editor’s note: For related content, see “

Diagnosing Pancreatic Lesions on Abdominal CT: Study Says Deep Learning System is Comparable to Radiologist Assessment

Could a New Deep Learning Tool Enhance CT Detection of Pancreatic Cancer?

In cases of early-stage colon cancer and acute diverticulitis, the study authors cautioned that subtle CT findings, such as adjacent fat stranding and focal bowel wall thickening, can be mistaken for peristaltic activity or be obscured by bowel filling. Braren and colleagues also noted that secondary changes like mesenteric stranding and abscess formation can be dominating features on CT in cases involving advanced colon cancer or complicated acute diverticulitis.

In regard to study limitations, the study authors acknowledged that broader application of the study results may be limited due to the AI model being trained and tested on a single institutional data set. They also noted that imaging features, such as fat stranding, may have been masked by adversarial noise (at a variance threshold of .01) that impacted the performance of the AI model. Noting that the study focused on the most frequent benign and malignant entities for bowel wall thickening, the study authors maintained that future studies should assess a broader array of malignant and benign entities and incorporate multiparametric data integration in order to evaluate and possibly improve the capabilities of the AI model.

Articles

Researchers showed that adjunctive use of a deep learning algorithm resulted in an eight percent increase in sensitivity and a nearly 10 percent increase in specificity for differentiating between colon carcinoma and acute diverticulitis on computed tomography (CT) scans.

CT Study Says Deep Learning Model Could Help Differentiate Between Acute Diverticulitis and Colon Carcinoma

Over 80 percent of radiology residents said artificial intelligence (AI) and machine learning (ML) should be included in the curriculum for radiology residency programs and 76 percent emphasized having a continuous course on these subjects that spans all four years of residency, according to a new survey.

The survey results, published recently in 

, were based on responses from 209 radiology residents representing 21 of 35 radiology residency programs in the Radiology Residency Education Research Alliance (RRERA). Ninety-eight respondents (47 percent) were in residency programs with more than 40 residents. The survey respondents included 79 first-year residents (38 percent), 48 second-year residents (23 percent), 42 fourth-year residents (20 percent) and 41 third-year residents (20 percent).

According to the survey, 75 respondents (36 percent) strongly agreed and 100 respondents (48 percent) agreed that AI and ML should be incorporated in the curriculum for radiology residency. Twenty-six respondents were neutral on the inclusion of AI and ML in their residency training.

When asked their preferred method of education on AI and ML, 141 respondents (67 percent) preferred hands-on and laboratory training, 127 residents (61 percent) opted for a lecture series and 86 respondents (41 percent) indicated preferences for in-house/institutional courses and online videos (whether they were available via YouTube or from professional societies). In regard to the goals of AI and ML education, 171 respondents (82 percent) wanted to be able to troubleshoot AI tools and assess whether they are working in practice. Twenty-five residents(12 percent) wanted to know how to utilize an AI tool in practice without a need to learn troubleshooting or evaluation of whether an AI system is working as intended.

“To the best of our knowledge, no prior study has surveyed radiology trainees regarding their preference for the depth of AI education or the expected outcome of such a curriculum,” wrote study co-author Lars J. Grimm, M.D., MHS, an associate professor of radiology at Duke University, and colleagues.

Assessing the Value Proposition of AI in Radiology

Recognizing and Addressing Biases with AI and Radiologists

Can AI Improve the Consistency of Breast Density Assessment by Radiologists?

Fifty-four survey respondents (24 percent) said their residency programs offered no resources for AI and ML as part of the curriculum. According to the study authors, 168 respondents (80 percent) said they had not been involved in AI or ML research and 107 residents (51 percent) had not used an AI or ML tool for work or research.

Researchers also noted a prevailing lack of awareness about currently available AI resources. Seventy-eight percent (163 residents) were not aware of AI-related videos offered by the Radiological Society of North America (RSNA), 86 percent (180 respondents) were not aware of the American College of Radiology’s (ACR) Data Science Institute, and 88 percent (183 residents) were unaware of an AI Journal club hosted by the Resident and Fellow Section of the ACR.

“These data demonstrate the need for improving awareness of existing AI education resources through better marketing/education as well as (identifying) opportunities for developing courses/curricula according to the preferred modes of learning reported by the residents,” noted Grimm and colleagues.

In regard to study limitations, the study authors acknowledged a possible selection bias with residents who are interested in AI being more likely to complete the survey. While 67 percent of respondents (141) indicated that hands-on training in AI/ML would be a preferred method of training, the researchers pointed out that only 10 percent (19) had experience with hands-on training on these topics. The study authors also noted that 27 percent of residents and 60 percent of radiology residency programs responded to the survey.

In a new survey, 83 percent of radiology residents agreed that artificial intelligence/machine learning (AI/ML) should be part of their curriculum but approximately 24 percent of residents said there are currently no AI/ML educational offerings in their residency program.

Is There Enough AI Emphasis in Radiology Residency Programs?

Eric Postal, MD, is a diagnostic radiologist with the University of Pittsburgh Medical Center. 

 TV series for much of the current millennium. I never got into the older stuff, and I might just be bowing out after the last couple of seasons. Still, I have put in enough time that I probably qualify as a fan.

, time travel is a central theme of the show. Sometimes it makes more sense than others. Given that actual time travel is not a real thing (as far as we know), the show can get away with making stuff up as it goes along. Who's to say it is any more or less accurate than the 

 franchise, or anything else dabbling with the concept?

Viewers aren't exactly watching such things for technical pointers. These shows or films are usually more about having fun with the concept, or provoking thought. Maybe I can thank that for my recent awareness that I have, in a way, been dabbling in radiological time travel.

Most of us do to a certain extent. Unless everything you do is in real time, like interventional stuff or good old-fashioned barium slinging, the images you are interpreting are a snapshot of the past. You might phrase your reports in the present tense, but your descriptions of pathology (or lack thereof) are only accurate as of whenever the patient was being imaged.

That doesn't matter so much if you read stuff in the STAT setting. If you have a super low turnaround time and your referrers see your report right away, everything is essentially happening "now." It's also not a big deal for non-emergent things like routine screenings or periodic surveillance of slow-moving pathology. If you read a study a couple days after it was done, and the referrer sees your negative report a few days after that, all is well.

It is more troublesome when some clinician suddenly wants results on something that was done a while ago but didn't get read yet. Another scenario may involve a routine exam from a couple of days ago that turns out to have an unexpected acute abnormality that warranted urgent action. It's as if a villain got ahold of time travel and used it for nefarious means. The good guys now have to scramble in an attempt to make up for the lost time.

My own recent time traveling radiology has been much more benign. I mentioned in recent columns that I have been doing some "internal moonlighting" to help with a perpetually accumulating glut of X-rays. In a typical day, many of the films I see are of patients who already went on to have follow-up studies via various modalities.

Sometimes, the subsequent X-rays have not been read yet either, and I will bundle them all together for a report that talks about how things have changed or remained stable as the hours (or days) went by between studies. Alternatively, other folks have already read the more recent stuff. I then get to generate my report knowing what happened in the future of the films I'm looking at.

I have considered the value of being dogmatically and intellectually honest about it. In other words, I would blind myself to what happened afterward and just give a standard interpretation of the past-tense X-ray in front of me. That would surely be the right thing to do if I were reading for pure academic or research purposes (or, God forbid, legal ones.)

That doesn't really help the referrers or patients though. The more actionable information I give them, the better. For instance, if I see yesterday's right mainstem bronchial intubation but I know that today's CT shows proper retraction, I don’t need to ring up the referrer to say the tube has to be pulled back.

For that matter, I should say in my report that, yes, the tube was malpositioned on that film, but it was already taken care of on the subsequent scan. Otherwise, some nurse getting ahold of my X-ray report and not knowing about the CT might dutifully page her house staff to tell them about a tube that needs no adjustment.

The thought has occurred to me that I probably spend too much time and effort on a lot of these past-tense films. My reports aren't exactly novels, but I'm still generating verbiage that somebody's going to have to read through just in case … and they already know what subsequent imaging showed. If I say nothing new, I am wasting my time and theirs. I might do better for everyone involved if I just had a macro like: "Study presented for interpretation after other imaging has already occurred. Please see report of subsequent exam."

 that my X-ray from the past showed nothing new or important without going over it. There is always a chance that I will see something a more recent study missed because of technical factors (or error on the part of another radiologist). It might just take me being the equivalent of a time traveler from the past to tell present-day people about a subtle fracture or tiny pneumothorax.

When you’re asked to review an X-ray for a patient who already had follow-up imaging, do you consider the results of follow-up imaging or evaluate the X-ray with fresh eyes?

Navigating the Radiology Conundrum of Reading X-Rays When Follow-Up Imaging Has Already Been Done

's Weekly Scan is your chance to catch up on the latest radiology content, from new research and device news to the latest case quizzes and conference reports. Review the slideshow below to see this week's top content:

Diagnostic Imaging's Weekly Scan: January 22-January 28

Slideshows

Catch up on the top radiology content of the past week.

In a new study comparing photon-counting detector computed tomography (PCD CT) to energy-integrating detector CT (EID CT) for thoracoabdominal CT angiography, researchers found a 25 percent higher contrast-to-noise ratio (CNR) with PCD CT and subsequently determined that a revised protocol with PCD CT could reduce iodinated contrast media (ICM) by 25 percent in comparison to EID CT.

Noting the potential risk for contrast-induced acute kidney injury (CI-AKI) in patients with multiple computed tomography angiography (CTA) exams, the researchers sought to develop and assess the use of PCD CT with a reduced ICM protocol in this patient population.

For the prospective study, which was recently published in 

, researchers assessed 100 patients (mean age of 75) who had CTA with PCD CT and prior EID CT for imaging of the thoracoabdominal aorta.

In the first group of 40 patients, the study authors noted the use of PCD CT with virtual monoenergetic images (VMI) at 50 keV had a 25 percent higher contrast-to-noise ratio (CNR) than EID CT. In the second group of 60 patients, the researchers found that a 25 percent reduction of ICM with PCD CT at VMI of 50 keV was non-inferior to EID CT for imaging of the thoracoabdominal aorta.

“Compared with EID CT, VMI at 50 keV from PCD CT had noninferior objective and subjective image quality, with mean differences in CNR and subjective image quality between EID CT and PCD CT at 50 keV being above the pre-defined boundaries of noninferiority …, illustrating the potential of PCD CT to reduce contrast media exposure to potentially susceptible patients,” wrote Hatem Alkadhi, M.D., MPH, EBCR, FESER, a professor of radiology at the Institute of Diagnostic and Interventional Radiology of the University Hospital Zurich in Switzerland, and colleagues.

Five Takeaways from New Consensus Recommendations for CT Imaging and Reporting in Patients with CAD

HeartFlow Garners FDA Clearances for Two AI-Powered Assessment Tools with CCTA

, James Dundas, MBBS, MRCP and Jonathon A. Leipsic, M.D., FRCPC, MSCCT., noted a number of potential benefits with PCD CT, ranging from virtual non-contrast imaging for coronary calcium scoring and reducing metallic artifacts in close proximity to implanted cardiac devices to utility in assessing myocardial fibrosis and complex congenital heart disease. While acknowledging the “framework” of the study’s findings with photon-counting CT, Drs. Dundas and Leipsic said measurable clinical impact demonstrated in future studies will be more of a driver for wider adoption than ICM reduction in aortic imaging.

“Delivering benefit in clinically relevant outcomes would make a stronger case for embracing photon counting in routine clinical practice,” noted Dr. Dundas, an advanced cardiac imaging fellow at the University of British Columbia, and Dr. Leipsic, a professor and head of the Department of Radiology at the University of British Columbia.

In regard to study limitations, the study authors acknowledged a small proportion of women in the study and the overall small cohort size. The researchers also noted the study was not designed to compare the diagnostic accuracy of photon-counting detector CT (PCD CT) versus energy-integrating detector CT (EID CT). Pointing out that their image quality comparison of PCD CT and EID CT was based on single-energy mode imaging, Alkadhi and colleagues maintained that future studies should assess dual-energy CT use as well as the impact of quantum iterative reconstruction (QIR) upon image quality.

Preliminary research suggests the use of photon-counting detector computed tomography (CT) may facilitate a 25 percent reduction of iodinated contrast media (ICM) in comparison to energy-integrating detector CT for angiographic imaging of the thoracoabdominal aorta.

Could Photon Counting Reduce Iodinated Contrast Media for CT Angiography?

Keya Medical has launched the DeepVessel FFR, a software device that utilizes deep learning to facilitate fractional flow reserve (FFR) assessment based on coronary computed tomography angiography (CCTA).

Cleared by the Food and Drug Administration (FDA), the 

 provides a three-dimensional coronary artery tree model and estimates of FFR CT value after semi-automated review of CCTA images, according to Keya Medical.

The company said the DeepVessel FFR has demonstrated higher accuracy than other non-invasive tests and suggested the software could help reduce invasive procedures for coronary angiography and stent implantation in the diagnostic workup and subsequent treatment of coronary artery disease.

Joseph Schoepf, M.D., FACR, FAHA, FNASCI, the principal investigator of a recent multicenter trial to evaluate DeepVessel FFR, says the introduction of the modality in the United States dovetails nicely with recent guidelines for the diagnosis of chest pain.

“I am excited to see the implementation of DeepVessel FFR. It comes together with the 2021 ACC/AHA Chest Pain Guidelines’ recognition of the elevated diagnostic role of CCTA and FFR CT for the non-invasive evaluation of patients with stable or acute chest pain,” noted Dr. Schoepf, a professor of Radiology, Medicine, and Pediatrics at the Medical University South Carolina.

Can Deep Learning Assessment of X-Rays Improve Triage of Patients with Acute Chest Pain?

New CT Protocol May Improve Diagnosis of Acute Chest Pain by 40 Percent

Employing deep learning capabilities, the DeepVessel FFR reportedly provides enhanced non-invasive evaluation of coronary arteries through semi-automated analysis of coronary computed tomography angiography (CCTA) imaging.

Could an Emerging Deep Learning Modality Enhance CCTA Assessment of Coronary Artery Disease?

The degree of background parenchymal enhancement (BPE) on contrast-enhanced mammography (CEM) is reportedly lowest during days eight through 14 of the menstrual cycle of premenopausal women with regular cycles.

This is one of the findings from a new retrospective study looking at the impact of clinical factors upon early BPE on CEM. For the study, recently published in the 

, researchers reviewed clinical data from the electronic medical records (EMRs) and imaging of 207 women (median age of 46) who had contrast-enhanced mammography exams between April 2020 and September 2021.

According to the study, the researchers used two different criteria to assess the degree of BPE with “criteria 1” involving dual-energy subtraction (DES) imaging of a standard craniocaudal image of the suspicious or affected breast, and “criteria 2” involving the greater degree of BPE on DES imaging of craniocaudal views of both breasts.

For both criteria, the study authors found a lower degree of BPE for older patients, those with a personal history of breast cancer and patients with a history of chemotherapy or radiation therapy. Patients with dense breasts had a higher degree of BPE, according to the researchers. The researchers also pointed out that postmenopausal and perimenopausal status had negative associations with BPE degree whereas premenopausal women with regular or irregular menstrual cycles had positive associations with BPE degree.

In the multivariable analysis, the study authors noted that menstrual status and timing of menstrual cycle were the only independent predictors of BPE degree. For premenopausal women with regular menstrual cycles, the researchers found the lowest degree of BPE occurred during days eight through 14 of the menstrual cycle.

“This finding may reflect fluctuation in circulating estrogen levels throughout the menstrual cycle and the effects of estrogen on vascularization. This association could inform decisions regarding scheduling of CEM examinations based on the time of the menstrual cycle,” wrote study co-author Yajia Gu, M.D., who is affiliated with the Department of Radiology at the Fudan University Shanghai Cancer Center in China, and colleagues.

(Editor's note: For related content, see "

Study Highlights Use of Contrast-Enhanced Mammography in Women with Breast Implants

Key Considerations with Implementing Contrast-Enhanced Mammography in Your Practice

Current Insights on Breast Density, Contrast-Enhanced Mammography and Supplemental Breast Cancer Screening

In regard to univariable analysis associations of younger age, dense breasts and premenopausal status that were linked to a higher degree of BPE in the study, Gu and colleagues said “ … these associations may represent decreases in estrogen hormone levels and in fibroglandular tissue as patients age.” However, noting the work of other authors who found no difference with BPE degree with respect to age in premenopausal and postmenopausal women, Gu and colleagues suggested that “ … menstrual status, which reflects hormonal status, may have a more direct influence on BPE than does age.”

Acknowledging the limitations of a retrospective study with a small sample size, the study authors also conceded patient selection bias with high proportions of women with newly diagnosed breast cancer as well as women with dense breasts in the study cohort. However, Gu and colleagues noted the focus of the study was on CEM, which was not employed for screening purposes during the study. The researchers noted they did not assess the relationship between BPE degree and additional risk factors for breast cancer, nor did they evaluate whether higher BPE affected cancer detection rates.

1. Wang S, Sun Y, You C, et al. Association of clinical factors and degree of early background parenchymal enhancement on contrast-enhanced mammography. 

. 2023 Jan 25. Doi: 10.2214/AJR.22.28769. Online ahead of print.

2. King V, Goldfarb SB, Brooks JD, et al. Effect of aromatase inhibitors on background parenchymal enhancement and amount of fibroglandular tissue at breast MR imaging. 

3. Zhao S, Zhang X, Zhong H, et al. Background parenchymal enhancement on contrast-enhanced spectral mammography: influence of age, breast density, menstruation status, and menstrual cycle timing. 

For premenopausal women with regular menstrual cycles, researchers have found a significant association between the timing of menstrual cycles and the degree of background parenchymal enhancement (BPE) on contrast-enhanced mammography (CEM).

Contrast-Enhanced Mammography Study Examines Impact of Clinical Factors on Background Parenchymal Enhancement

's Advances in AI monthly roundup is your chance to catch up on the latest AI news, AI-powered imaging modalities and emerging AI research affecting the field of radiology. Review the slideshow below to see highlights from the past month.

Diagnostic Imaging's Advances in AI: January 2023

Catch up on the top AI-related news and research of the past month.

Is dynamic abbreviated magnetic resonance imaging (MRI) a viable alternative for diagnosing early-stage hepatocellular carcinoma (HCC)?

In a retrospective multicenter study, recently published in 

, researchers assessed the use of dynamic abbreviated MRI for the detection of early-stage HCC among patients with cirrhosis who had liver transplant or resection.

 The study cohort was comprised of 161 patients with early-stage HCC (median age of 62) and 138 patients (median age of 55) who did not have HCC. For the simulated dynamic abbreviated MRI, researchers selected and reviewed coronal T2-weighted and axial 3D, fat-suppressed T1 dynamic, contrast-enhanced sequences at pre-contrast, late arterial, portal venous and delayed phases from preoperative MRI examinations, according to the study.

Employing liver pathologic findings as a reference standard, the study authors noted a sensitivity rate of 88.2 percent and a specificity rate of 89.1 percent for dynamic abbreviated MRI in the diagnosis of early-stage HCC.

Citing a variety of benefits, the researchers suggested the technology could be easily incorporated into workflows at MRI facilities with minimal training.

“The imaging protocol can be easily replicated at most MRI facilities by using 1.5-T or 3.0-T scanners equipped with standard three-dimensional T1-weighted gradient-echo sequences,” wrote lead study author Takeshi Yokoo, M.D., Ph.D., the medical director of MRI at the Harold C. Simmons Comprehensive Cancer Center in Dallas, and an associate professor of radiology at the University of Texas Southwestern Medical Center, and colleagues. “The workflow is non-disruptive, and the need for technologist education is minimal. LI-RADS (Liver Imaging Reporting and Data System) interpretation of dynamic abbreviated MRI is analogous to multiphase CT interpretation and offers all LI-RADS major features needed for category LR-5 classification.”

The researchers also maintained that abbreviated MRI could be an alternative to ultrasound for HCC screening and surveillance in obese patients and those with non-viral etiologies of cirrhosis.

“We did not find the sensitivity of abbreviated MRI to be modulated by obesity or by cause of cirrhosis, an important finding considering that (ultrasound) has worse visualization and performance in patients with obesity and those with non-viral causes of cirrhosis,” noted Yokoo and colleagues.

“Our findings therefore suggest that abbreviated MRI may serve as a viable surveillance strategy in these patients in whom (ultrasound) may be problematic.”

However, the researchers did acknowledge variation in the sensitivity rates for abbreviated MRI in regard to the Child-Pugh scoring system for cirrhosis. For patients with Child-Pugh class A cirrhosis, Yokoo and colleagues found high sensitivity rates for a variety of lesion sizes (83.3 percent for 1 to 1.9 cm tumors; 96.8 percent for 2 to 2.9 cm tumors; and 98.1 percent for tumors 

 3 cm). The authors also found moderate sensitivity for Child-Pugh class B and C cirrhosis (61.1 percent for 1 to 1.9 cm tumors; 64.3 percent for 2 to 2.9 cm tumors; and 71.4 percent for tumors 

(Editor's note: For related articles, see "

Could Contrast-Enhanced Ultrasound with Perfluorobutane Provide a Viable Option for Diagnosing Hepatocellular Carcinoma?

Study Says Machine Learning MRI Model May Help Predict Recurrence Risk of Hepatocellular Carcinoma

While noting the potential of dynamic abbreviated MRI for diagnosing HCC in patients with compensated cirrhosis, Yokoo and colleagues said prospective studies are necessary to validate their findings and provide clarity into the lower sensitivity they noted in patients with decompensated cirrhosis.

, Harrison Kim, Ph.D., M.B.A., said it remains to be seen whether abbreviated MRI would be a more cost-effective option for HCC surveillance in comparison to computed tomography (CT) or contrast-enhanced ultrasound.

“Although MRI cost varies across different countries and facilities, it is unlikely that the cost will be less than that of a CT or contrast-enhanced (ultrasound) examination, even after being reduced by 30%,” noted Dr. Kim, a professor in the Division of Advanced Medical Imaging Research in the Department of Radiology at the Heersink School of Medicine at the University of Alabama at Birmingham. “Although MRI generally yields higher contrast than CT, four-phase dynamic CT has demonstrated comparable accuracy with MRI in detecting HCC. CT is faster than abbreviated MRI for active HCC surveillance (10 minutes vs. 20 minutes) with minimal motion artifact and without inducing claustrophobia.”

1. Yokoo T, Masaki N, Parikh ND, et al. Multicenter validation of abbreviated MRI for detecting early-stage hepatocellular carcinoma. 

. 2023 Jan 24;220917. doi: 10.1148/radiol.220917. Online ahead of print.

2. Chong N, Schoenberger H, Yekkaluri S, et al. Association between ultrasound quality and test performance for HCC surveillance in patients with cirrhosis: a retrospective cohort study. 

3. Schoenberger H, Chong N, Fetzer DT, et al. Dynamic changes in ultrasound quality for hepatocellular carcinoma screening in patients with cirrhosis. 

4. Kim H. The feasibility of abbreviated MRI for active surveillance of hepatocellular carcinoma. 

 2023 Jan 24;223113. doi: 10.1148/radiol.223113. Online ahead of print.

In a multicenter study involving nearly 300 patients, researchers found that abbreviated magnetic resonance imaging (MRI) had a sensitivity rate of 88.2 percent and a specificity rate of 89.1 percent for detecting early-stage hepatocellular carcinoma (HCC).

Abbreviated MRI and Early-Stage Hepatocellular Carcinoma: What a New Multicenter Study Reveals

Emerging research suggests that magnetic resonance imaging (MRI) guidance may be more advantageous than computed tomography (CT) guidance for reducing the side effects of stereotactic body radiation therapy (SBRT) in the treatment of prostate cancer.

Results from the phase 3 randomized trial, recently published in 

, showed that MRI guidance for SBRT led to a significantly reduced acute grade 2 or greater genitourinary (GU) toxicity rate (24.4 percent) versus that of CT guidance (43.4 percent). Researchers also noted no acute grade 2 or greater gastrointestinal (GI) toxic effects with MRI guidance in comparison to a 10.5 percent toxicity rate for CT guidance.

In a recent video interview, lead study author Amar Kishan, M.D. called the MRIdian LINAC (ViewRay) a “major technological breakthrough” that allows physicians to combine continuous MRI imaging with a more targeted radiation delivery system for 

“(With) these advanced precision and accuracy capabilities, particularly that high degree of tracking during the treatment, we felt we could reduce the margins around the prostate that we need to treat from four millimeters to two millimeters,” explained Dr. Kishan, an associate professor, vice-chair of Clinical and Translational Research and chief of the Genitourinary Oncology Service within the Department of Radiation Oncology at UCLA.

For more insights from Dr. Kishan, watch the video below.

Videos

In a recent video interview, Amar Kishan, M.D., discussed a new study that demonstrated significant side effect reduction when utilizing magnetic resonance imaging (MRI) guidance instead of computed tomography (CT) guidance for stereotactic body radiation therapy (SBRT) to treat localized prostate cancer.