ARTICLE IN PRESS

Special Review

Structured Reporting in Radiology

Dhakshinamoorthy Ganeshan, MD, Phuong-Anh Thi Duong, MD, Linda Probyn, MD,
Leon Lenchik, MD, Tatum A. McArthur, MD, Michele Retrouvey, MD, Emily H. Ghobadi, MD,
Stephane L. Desouches, DO, David Pastel, MD, Isaac R. Francis, MBBS

Radiology reports are vital for patient care as referring physicians depend upon them for deciding appropriate patient management.
Traditional narrative reports are associated with excessive variability in the language, length, and style, which can minimize report clarity
and make it difficult for referring clinicians to identify key information needed for patient care. Structured reporting has been advo-
cated as a potential solution for improving the quality of radiology reports. The Association of University Radiologists—Radiology Research
Alliance Structured Reporting Task Force convened to explore the current and future role of structured reporting in radiology and sum-
marized its finding in this article. We review the advantages and disadvantages of structured radiology reports and discuss the current
prevailing sentiments among radiologists regarding structured reports. We also discuss the obstacles to the use of structured reports
and highlight ways to overcome some of those challenges. We also discuss the future directions in radiology reporting in the era of
personalized medicine.
Key Words: Radiology; structured reports; patient care; research; patient-centered radiology.
© 2017 The Association of University Radiologists. Published by Elsevier Inc. All rights reserved.

INTRODUCTION imperative for the reports to be timely and accurate and to

answer the clinical question. For a health-care system, these

T
he radiology report is vital for patient management.
may be the most important, readily available metrics by which
Radiologists play a major role in patient care by the
the value of radiology service could be measured.
accurate interpretation of imaging studies and appro-
Although learning how to report imaging studies is an es-
priate communication of imaging findings to referring
sential component of radiology residency training programs,
physicians. Although some referring clinicians may interpret
formal training on how to frame a radiology report often re-
imaging studies by themselves, radiologists’ reports have been
ceives less than 1 hour/year (6). Instead, most trainees learn
shown to be more accurate and comprehensive, resulting in
the art of reporting by observing faculty, senior residents,
improved patient care (1–5). To improve patient care, it is
fellows, and peers.
Traditionally, radiology reports were created using free-
Acad Radiol 2017; ■:■■–■■
text, narrative language. Studies show that the use of
From the Department of Diagnostic Radiology, University of Texas MD Anderson
Cancer Center, Pickens Academic Tower, 1400 Pressler Street, Unit 1473, nonstructured reports using narrative language may serve as
Houston, TX 77030-4009 (D.G.); Department of Radiology and Imaging Sciences an obstacle to optimal patient care. Excessive variability in lan-
Diagnostic Radiology, Emory University, Atlanta, Georgia (P.-A.T.D.);
Postgraduate Medical Education, Admissions and Evaluation, Sunnybrook
guage, length, and style can minimize report clarity, making
Health Sciences Centre, Education, Department of Medical Imaging, University it difficult for referring physicians to identify key informa-
of Toronto, Toronto, Ontario, Canada (L.P.); Department of Radiology, Wake tion needed for patient care (7–10).
Forest School of Medicine, Winston-Salem, North Carolina (L.L.); Department
of Diagnostic Radiology, Musculoskeletal Imaging, The University of Colorado, Structured reporting has been advocated as a potential so-
Denver, Colorado (T.A.MA.); Department of Radiology, Eastern Virginia Medical lution for improving the quality of radiology reports. A tiered
School, Norfolk, Virginia (M.R.); Department of Radiology, Northwestern
Memorial Hospital, Chicago, Illinois (E.H.G.); Department of Radiology, University
approach to structured reporting has been described (7,11–13).
of Missouri Kansas City School of Medicine, Kansas City, Missouri (S.L.D.); At its basic level, a structured report should be organized with
Radiology and Neurology, Dartmouth-Hitchcock Medical Center, Lebanon, New headings, such as clinical history, indication, technique, find-
Hampshire (D.P.); Department of Radiology, University of Michigan Hospitals,
Ann Arbor, Michigan (I.R.F.). Received May 31, 2017; revised August 2, 2017; ings, and impression (Fig 1). The next tier of structured reports
accepted August 3, 2017. Submission declaration: All the authors confirm that is where the “findings” section is organized with subhead-
this manuscript has not been published previously, and that it is not under
consideration for publication elsewhere, that its publication is approved by ings, such as the various organs (or anatomic structures) imaged
all authors and tacitly or explicitly by the responsible authorities where the (Fig 2). At the highest tier, the structured radiology report
work was carried out, and that, if accepted, it will not be published else-
where including electronically in the same form, in English or in any other
has all of the previously mentioned characteristics and uses a
language, without the written consent of the copyright holder. Compliance with standardized language based on a universally accepted lexicon
ethical standards: All the authors confirm that this manuscript complies with (Fig 3). Increasingly, academic centers are using structured ra-
ethical standards. Dhakshinamoorthy Ganeshan was supported by P30 Cancer
Center Support Grant No. NIH/NCI P30 CA016672 from the National Cancer diology reports containing templates, macros, or prepopulated
Institute, National Institutes of Health. Address correspondence to: D.G. e-mail: checklists.
dganeshan@mdanderson.org
The Association of University Radiologists—Radiology Re-
© 2017 The Association of University Radiologists. Published by Elsevier Inc.
All rights reserved.
search Alliance convened a task force to review the current
https://doi.org/10.1016/j.acra.2017.08.005 status of structured reports in radiology. In the present article,

1
GANESHAN ET AL
Figure 1. Example of a radiology report using basic headings. CT,
computed tomography.
we review the evidence supporting the use of structured
radiology reports, and discuss its pros and cons and the current
prevailing sentiments among radiologists regarding struc-
tured reports. We describe some ways to overcome challenges
and successfully implement structured reporting in daily practice
2
Academic Radiology, Vol ■, No ■■, ■■ 2017
and discuss the future of radiology reports in the modern era
of precision medicine.
ADVANTAGES OF STRUCTURED REPORTING
A review of literature shows that structured reports have many
advantages for radiologists as well as referring physicians
(Table 1). Both radiologists and referring clinicians are in-
terested in reducing the rate of diagnostic errors, which for
radiologist accounts for as much as 4% of reports (14–18). One
of the most common causes for malpractice lawsuits against
radiologists is a missed diagnosis (19–22).
Although diagnostic errors in radiology are multifactorial,
an important contributing factor is cognitive bias, arising from
the radiologist’s “satisfaction of search” (23). This error occurs
when a radiologist prematurely stops “searching” for diag-
noses, after making the initial diagnosis, based on clinical history.
Using a checklist and a systematic search pattern may help
to avoid such diagnostic errors (24–27). In a retrospective review
of 3000 lumbar spine magnetic resonance imaging (MRI)
Figure 2. Example of a structured radiology report
using subheadings specifying organs and the organ
system within the findings section. CT, computed
tomography.
Academic Radiology, Vol ■, No ■■, ■■ 2017
Figure 3. Example of a structured radiology report using standardized language and management recommendations. BI-RADS, Breast
Imaging Reporting and Data System.
TABLE 1. Benefits and Limitations of Structured Radiology Reports
Benefits
Disease-specific report templates can improve report clarity and
quality, and ensure consistent use of terminology across practices.
Checklist style reports can reduce diagnostic errors (such as failing to
report incidental renal cell carcinoma in a magnetic resonance spine
performed for back pain).
Can reduce grammatical and nongrammatical digital speech
recognition errors
Ensures completeness of radiology report documentation and thereby
improves radiology reimbursement
May be financially rewarding under the new Medicare Merit-based
Incentive Payment System
Positively impacts research in radiology by facilitating data mining
Provides opportunities for quality improvement
Can help promote evidence-based medicine by integrating clinical
decision support tools with radiology reports
examinations, structured reporting helped identify clinically
significant extraspinal findings in 28.5% of the patients, which
were not included in the original unstructured report (26).
Another study of spine MRI reports found a 38.6% error rate
for potentially important extraspinal findings (27). Similarly,
the use of a checklist-style structured report template has been
shown to improve the rate of diagnosis of non–fracture related
findings on cervical spine computed tomography (CT) (25).
Ideally, structured reports should use a standard lexicon and
should incorporate evidence-based recommendations. Such
an approach may not only reduce errors but also help improve
the overall quality of the reports. For example, applying
STRUCTURED REPORTING IN RADIOLOGY
Limitations and Challenges
Radiologists may be resistant to change.
Learning curve associated with new reporting style may
negatively impact radiology workflow and productivity.
Potentially increased error rates if used improperly (eg,
failing to remove the prepopulated phrase of “normal
gallbladder” in a patient who is status post
cholecystectomy).
Interruption of visual search pattern may increase
reporting time.
Including unnecessary or irrelevant information in a
template report may negatively impact the coherence of
the report and its subsequent comprehension by
referring physicians.
American College of Radiology Lung CT Screening Re-
porting and Data System increased the positive predictive value
for diagnosing malignancy from 6.9% to 17.3% in 1603 pa-
tients with follow-up (28). Another study of knee MRI
structured reports showed a significant reduction in diagnos-
tic errors as well as an improvement in report quality and
content (29).
Another advantage of structured report templates is that they
prompt radiologists to incorporate the key imaging findings
required from a particular examination and clinical condi-
tion. In a study of structured reporting for CT coronary
angiography, referring physicians’ comprehension of the degree
3
GANESHAN ET AL
of stenosis of major coronary arteries was improved when
structured reports were used (30). Similarly, structured reports
have been shown to enhance the clinical impact in tumor
staging and surgical planning for pancreatic and rectal carci-
noma (31–33). For example, a recent study showed that less
than 50% of free-text CT reports used for pancreatic cancer
staging included the standard terminology for vascular in-
volvement, a key component for determining resectability (32).
Such deficiencies can be overcome by using structured report
templates. Brook et al. compared the results of structured versus
nonstructured reporting of CT findings for the staging and
subjective assessment of resectability for pancreatic adenocar-
cinoma (31). They concluded that surgeons were more
confident about tumor resectability using structured reports
compared to nonstructured reports. Similarly, Sahni et al.
showed that the use of a structured MRI report improved
rectal cancer staging compared to the use of a free-text format
(33). When assessed by abdominal radiology subspecialists, the
optimal report rate improved from 38% to 70% after the im-
plementation of a structured report template (33).
Structured reports also decrease the incidence of syntactic
and semantic errors. A high percentage (4%–60%) of free-
text reports is associated with grammatical and nongrammatical
digital speech recognition errors (34–36). Although most ty-
pographic errors are not clinically significant, they undermine
the confidence of referring physicians and patients about the
overall accuracy of the radiological interpretation. Struc-
tured reports have been shown to reduce nongrammatical
errors, including both omission and commission errors (37).
Finally, structured reports may be financially rewarding. A
recent study found that 20% of abdominal ultrasound reports
had incomplete documentation, resulting in up to 5.5% losses
in reimbursement (38). Importantly, the deficiency was usually
due to preventable causes, such as not mentioning the spleen.
By reminding the radiologist to comment on specific organs
(or other relevant anatomic structures), structured reports lead
to improved documentation and reimbursement.
OBSTACLES TO STRUCTURED REPORTING
Structuring radiology reports have many benefits but have not
yet found universal acceptance among radiologists (39,40). A
survey of 265 academic radiologists from United States found
that only 51% used structured radiology reports consistently,
whereas 33% used it infrequently. In the same study, only 60%
were satisfied with structured reports, whereas 27% were neutral
or undecided and 13% were dissatisfied (40). Similar results
have also been reported in studies conducted in other countries.
For example, a survey of 1159 Italian radiologists found that
56% of the radiologists never used structured radiology reports
(39). Another similar study conducted in Belgium found that
only 55% of the 132 radiologists surveyed felt that struc-
tured reports for complex examinations such as CT and MRI
were a good idea (41).
There are many reasons why radiologists have not fully ac-
cepted the structured reporting practice (12,42). There are
4
Academic Radiology, Vol ■, No ■■, ■■ 2017
numerous unique reporting styles among radiologists. Radiology
reports are the means through which radiologists demon-
strate their breadth of knowledge, as well as descriptive and
diagnostic capabilities (43). Reports form the basis of how ra-
diologists’ competence is judged by referring physicians,
colleagues, and patients. Having been used to a particular style
of reporting, radiologists may be resistant to change, espe-
cially when they feel there is no clinical necessity for change
(12,42,44). Radiologists value their freedom of expression and
may perceive structured reporting as an attack on their au-
tonomy and the art of medicine. Some radiologists feel that
using structured templates may contribute to commoditization
of the specialty and can downgrade the quality of subspecialist
reads by limiting the scope of what they can include
(12,39,40,42,44).
Another obstacle to structured reports is the time and
effort required to develop report templates and the negative
impact this may have on productivity. Furthermore, altering
ingrained work habits may be associated with a steep
learning curve, requiring significant time commitment (40).
This concern about the potential loss of productivity may
lead to radiologists preferring to continue with free-text
dictations for their perceived ease, speed, and familiarity
(12,40,42,43).
Adherence to rigid structured report templates may result
in an interruption of the visual search pattern. A phenome-
non known as “eye dwell” occurs when radiologists are inclined
to keep their eyes focused on the report template rather than
the images, contributing to missed findings (43). Radiolo-
gists may be distracted from image interpretation by focusing
on template adherence. If the templates are not user-
friendly or if a template follows a different order from which
the radiologist is accustomed to, this may lead to altered search
patterns and an overall increased duration of image interpre-
tation (45). The “eye-dwell” phenomenon is an even greater
problem for radiologists without access to voice activated tem-
plates and macros (45). Templates may also potentially increase
report errors when preloaded phrases are not appropriately
omitted from the final report (40).
Report templates may be more useful for less complex studies
such as x-rays or ultrasound rather than more complex studies
such as CT or MRI. For especially complicated cases, tem-
plates may not be comprehensive enough to include all of
the necessary information (40). For additional information to
be included, multiple additional drop-down menus, key-
board commands, and extra mouse clicks may be required,
contributing to inefficiency (12,45). By including unneces-
sary or irrelevant information, report templates may negatively
impact the coherence of the report and its subsequent com-
prehension by referring physicians. For example, a rigid organ-
based template may necessitate dictating about the incidental
thyroid nodules, benign pericardial cyst, numerous liver and
renal cysts, and various other completely irrelevant findings
in multiple organs before describing the large ovarian tumor
with carcinomatosis and bowel obstruction. Descriptions of
disease processes that affect multiple organ systems may be
Academic Radiology, Vol ■, No ■■, ■■ 2017
unnaturally divided by the organ system rather than discussed
as an overall disease process, making reports harder to com-
prehend (43). Indeed, the survey from Italian radiologists
confirmed that oversimplification and the rigid nature of the
structured reports were the most common reasons why ra-
diologists did not use them (39). Continuous revision of
structured templates can be tedious, especially in busy prac-
tices, resulting in further obstacles for widespread adoption
(40).
Although some studies describe referring physicians’ pref-
erence for structured reports, there is no agreement on the
format of that structured report. One study concluded that
referring clinicians and radiologists preferred the standard item-
ized report with subheadings for each organ and the use of
free-text over the “point-and-click” reports, with clickable
options of standardized texts underneath each subheading (46).
Some argue that the use of a structured report may not nec-
essarily improve the comprehension of the report nor decrease
its reading time by the referring physicians (47,48). Sistrom
and Honeyman-Buck evaluated the impact of structured re-
porting on the comprehension and speed for reading radiology
reports by senior medical students and found no evidence to
support one report format over another (48). Similarly,
Krupinski et al. showed that the radiology report format did
not shorten the reading time or improve the comprehen-
sion of the material (47).
Some studies also report that structured reports may be
inferior to free-text reports (49,50). A cohort study of resi-
dent reports using narrative dictation versus a commercially
available structured reporting system found that structured
reporting resulted in a decrease in report completeness and
accuracy, which could affect patient care (49). Accuracy
scores for generated reports were 88.7 for the structured
report group and 92.4 for the narrative group (P < 0.001).
Completeness scores for generated reports were 54.3 for the
structured group and 71.7 for the narrative group (P < 0.001).
Comparing the two groups between phases 1 and 2, four
months apart, showed decreased accuracy and completeness
scores for structured reports. Many residents found that the
structured system was too constraining and time-consuming
(49). However, it should be noted that this was a relatively
old study and the current technology may offer more user-
friendly interfaces for creating structured reports, thereby
eliminating or minimizing some of the problems mentioned
previously. Vache et al. found that the subjective Likert
scoring was more accurate than the structured report using
the Prostate Imaging—Reporting and Data System (PIRADS)
lexicon (50). Although these classification systems are evolv-
ing (the original PIRADS 1 has now been replaced with
PIRADS 2), newly introduced disease-specific structured
templates warrant thorough validation before they can be
accepted as standard of care.
Finally, even when standardized reporting is validated and
mandated, there is no assurance for its proper use. For in-
stance, an international study analyzing mammographic reports
after the implementation of the Breast Imaging Reporting and
STRUCTURED REPORTING IN RADIOLOGY
Data System (BI-RADS) found reports with incomplete
content, especially among community practices (51).
OVERCOMING CHALLENGES
Although the widespread adaptation of structured reporting
in radiology has been challenging, structured reporting in breast
imaging is one notable exception. The history of BI-RADS
serves as an excellent example of how structured radiology
reporting can be successfully incorporated in clinical prac-
tice (52). Many leaders in breast imaging championed the need
for a reporting style that was not only clear and concise but
also guided patient management. This is the most important
message from BI-RADS success story—radiology reports must
impact patient care.
The importance of using structured reports has been em-
phasized by various professional societies including the
Radiological Society of North America (RSNA). The “RSNA
Reporting Initiative” aims to improve radiology practice with
a library of structured report templates (53,54). Expert panels
of subspecialty radiologists helped create more than 200 report
templates, freely available from the RSNA (55). Similar ini-
tiatives have been taken in other radiological societies such
as the Society of Abdominal Radiology, which has resulted
in the creation of disease-specific report templates (56).
To successfully implement structured reporting at the in-
stitutional level, radiology leadership should identify areas where
structured radiology reporting may be especially useful. This
may require committees with subspecialty expertise (57). It
is extremely important to collaborate with the referring phy-
sicians and to obtain their input in developing disease-
specific report templates, referring physicians to ensure that
the structured radiology report captures all the essential in-
formation required for patient management (58). Structured
templates available from various national societies can be modi-
fied based on local needs. For example, referring physicians
at tertiary cancer centers may consider potential curative treat-
ment in surgical cases deemed unresectable at other institutions.
In such circumstances, the format and content of the struc-
tured radiology report would need to be modified to provide
all additional details concerning resectability.
Once the contents of a report template are decided, input
should be obtained from all the radiologists who would be
using the template (57). In particular, any concern about ef-
ficiency should be addressed. Voice recognition software for
radiology dictation also allows for easier distribution and uti-
lization of structured reports. Many newer software packages
include options to link specific premade reports to specific
exams (such as chest radiograph or CT abdomen) so that when
the study is opened, the macro automatically populates without
having to search through a list of templates. Within these tem-
plates, quick pick lists can be added, allowing for specific phrases
to be selected. Adopting such techniques, which make it rel-
atively easy to use structured report templates, may convince
more radiologists to transition to a structured reporting style.
The optimal use of structured radiology reports may require
5
GANESHAN ET AL
the creation of numerous disease-specific report templates and
the installation of specific examination codes that would need
to be tailored to the study protocol (58). Natural language
processing might be potentially helpful in this regard. Through-
out the implementation phase of structured reports, it is vital
that adequate information technology support is always avail-
able for any troubleshooting.
It may be helpful to allow for a certain degree of auton-
omy for radiologists to use free text within the structured
template report, where it is deemed necessary. Further, it may
be worthwhile to consider introducing structured reports in
a phased manner to alleviate the concern among radiologists
regarding the potential decrease in productivity when switch-
ing to a new style of reporting (57).
Attaching financial incentives such as faculty bonuses to
promote the use of structured reporting has been men-
tioned in the literature, although this may not always be
necessary (57,59). Using data from a peer review process ap-
propriately may be another method to help convince radiologists
to use structured reporting. For example, if the peer review
data show that a significant percentage of radiologists miss bone
metastases on CT scans, sharing these data would perhaps make
the radiologists more open to using structured itemized reports
as the structured checklist style reports would help over-
come such diagnostic errors of oversight.
FUTURE DIRECTIONS
The radiology report is the single most important deliver-
able radiologists create to connect with referring physicians
and patients. Working with referring physicians to improve
the clarity and the consistency of radiology reports through
structured reporting is critically important as we move from
a volume-based to a value-based reimbursement model with
specific quality metrics. The future where we are reim-
bursed based on the inclusion of particular words in our reports
is already upon us. Data extraction from structured reports
provides a means of capturing the quality metrics necessary
for reimbursement, which will become increasingly impor-
tant as many radiology practices begin to participate in the
Merit-based Incentive Payment System (MIPS) part of the
Medicare Access and CHIP Reauthorization Act (60).
Several of the proposed quality measures for MIPS require that
information or follow-up recommendations are included in the
radiology report. These include use of a standardized nomen-
clature for imaging study type, tracking the number of past
examinations using ionizing radiation, and the inclusion of follow-
up recommendations for pulmonary nodules, based on nodule
size and patient risk (60). Structured reporting not only in-
creases the likelihood that these data will be included, but it
also makes it easier to search for such information.
Structured reports may also be used to automate critical result
notification or imaging follow-up. For example, Choksi et al.
advocate adding a mandatory numerical coding system to the
radiology report to flag unexpected findings (61). The reports
would be mined by the cancer registrar who would alert the
6
Academic Radiology, Vol ■, No ■■, ■■ 2017
referring clinician if no follow-up was scheduled within 2
weeks. Such a coding system could also be automated to send
a communication to the patient to follow up on the exam-
ination with their physician. Other studies have also reported
the utility of integrating such coding system with radiology
reports to improve communication findings of possible neo-
plasms and monitoring of suspected cancers (62).
For tumor imaging, radiologists commonly measure ref-
erence lesion on picture archiving and communication system
(PACS) or a 3D software package, compare the measure-
ment to a prior study, and dictate the data into the report.
Unfortunately, this approach is highly inefficient and prone
to transcription errors. A standardized lesion management tool
may be used for quantitative reporting by capturing and or-
ganizing structured measurement data, thereby eliminating
human rounding and dictation errors (63). The Annotation
and Image Markup (AIM) project of the National Institutes
of Health Cancer Biomedical Informatics Grid was created
to allow for quantitative imaging to be stored in a uniform
machine-readable format (64). Although not yet widely in-
tegrated into radiology practices, early work using the AIM
format with oncological imaging demonstrates that this format
improves efficiency, reduces error, and facilitates research. Using
the AIM standard, large quantities of data could be mined with
little human effort. Structured reports using the AIM format
can also seamlessly capture and organize important quantita-
tive imaging data from nononcological imaging studies (eg,
cardiovascular CT or MRI), such that referring physicians are
able to easily retrieve the key information required for patient
management (64). Structured report templates may also be
potentially integrated with decision support tools to improve
diagnostic performance and to provide consistent recommen-
dations for follow-up (65).
It may be feasible to develop computer-assisted reporting
and decision support framework that can systematically in-
tegrate clinical guidelines into the voice recognition software
or PACS, so that these can act as decision support tools during
image interpretation (65). For example, when a radiologist
is interpreting an adrenal lesion on CT, the decision support
tools may mandate the radiologist to provide specific descrip-
tors such as size, attenuation, enhancement pattern, and stability,
and may help to consistently classify these into benign, ma-
lignant, or indeterminate (requiring follow-up or further
evaluation). Similarly, structured reports may be integrated
with an online evidence-based decision support system and
other artificial intelligence expert systems that may help reduce
cognitive bias, improve diagnostic performance, and promote
the practice of evidence-based medicine (66,67).
Radiology reports provide additional opportunities for in-
novation, including multimedia-enhanced reports (68,69). In
these reports, key images would be marked during interpre-
tation and a hyperlink to these images would be embedded
in the final report. Graphs of serial measurements may also
be incorporated. One study showed that 80% of referring phy-
sicians preferred multimedia reports over the reports and would
preferentially refer patients to facilities that used such reports
Academic Radiology, Vol ■, No ■■, ■■ 2017
(68). Oh et al. have developed a prototype report that
hyperlinks medical terms to patient-friendly explanations (70).
There are many commercial products that offer graphical
enhancements to radiology reports and provide data mining
opportunities. One such system captures key medical images
and voice descriptions, and subsequently tag images with
metadata describing anatomic locations and diagnoses, result-
ing in a multimedia radiology report (71). By linking image
findings from multiple serial studies, the radiology report can
provide a graphical display of the disease timelines, thereby
providing a comprehensive picture of the entire course of the
disease (65). Such multimedia-enhanced structured reports may
also serve as powerful tools in data mining for population out-
comes and help create robust disease models, which may help
improve patient management.
Use of structured radiology reports is important in our pursuit
for practicing precision medicine. Unstructured radiology reports
make data mining extremely difficult. The lack of a consis-
tent terminology in unstructured reports hinders data mining
and may require specialized algorithms and extensive manual
input and natural language processing to extract informa-
tion. In contrast, data mining from structured reports are more
easy and accurate due to homogeneity in the language used
in the reports. For example, obtaining data such as the inci-
dence of coarse heterogeneous calcification in mammograms
in patients with BReast CAncer susceptibility gene (BRCA)-
positive breast cancer and correlating these data with patient
outcome would be relatively straightforward from struc-
tured mammogram reports. However, performing the same
analysis from unstructured radiology reports that do not use
the standard lexicon could be a herculean task. Further, in-
corporating structured radiological reports with other data from
electronic health records such as environmental risk factors,
genomics, and histopathology can help pave the way for per-
sonalized medicine.
In conclusion, structured radiology reports offer unique op-
portunities to improve the quality of a radiology report. By
using standardized terminology, structured reports enhance
clarity and improve communication of radiological findings.
Ease of data mining from structured reports can significantly
enhance research and quality assurance initiatives. Although
structured radiology reporting faces challenges such as de-
personalization of radiology reports and workflow and
productivity issues, these problems can be overcome with con-
certed effort from the radiology community. Promoting further
research evaluating the impact of structured radiology re-
porting on patient outcomes may help increase its use across
radiological practices worldwide.
REFERENCES
1. Alfaro D, Levitt MA, English DK, et al. Accuracy of interpretation of cranial
computed tomography scans in an emergency medicine residency
program. Ann Emerg Med 1995; 25:169–174.
2. Arhami Dolatabadi A, Baratloo A, Rouhipour A, et al. Interpretation of
computed tomography of the head: emergency physicians versus radi-
ologists. Trauma Mon 2013; 18:86–89.
STRUCTURED REPORTING IN RADIOLOGY
3. Gatt ME, Spectre G, Paltiel O, et al. Chest radiographs in the emergen-
cy department: is the radiologist really necessary? Postgrad Med J 2003;
79:214–217.
4. Kang MJ, Sim MS, Shin TG, et al. Evaluating the accuracy of emergen-
cy medicine resident interpretations of abdominal CTs in patients with
non-traumatic abdominal pain. J Korean Med Sci 2012; 27:1255–1260.
5. Weiner SN. Radiology by nonradiologists: is report documentation ad-
equate? Am J Manag Care 2005; 11:781–785.
6. Sistrom C, Lanier L, Mancuso A. Reporting instruction for radiology resi-
dents. Acad Radiol 2004; 11:76–84.
7. Bosmans JM, Weyler JJ, Parizel PM. Structure and content of radiolo-
gy reports, a quantitative and qualitative study in eight medical centers.
Eur J Radiol 2009; 72:354–358.
8. Heikkinen K, Loyttyniemi M, Kormano M. Structure and content of 400
CT reports in four teaching hospitals using a new, Windows-based soft-
ware tool. Acta Radiol 2000; 41:102–105.
9. Naik SS, Hanbidge A, Wilson SR. Radiology reports: examining radiol-
ogist and clinician preferences regarding style and content. AJR Am J
Roentgenol 2001; 176:591–598.
10. Wallis A, McCoubrie P. The radiology report—are we getting the message
across? Clin Radiol 2011; 66:1015–1022.
11. Bosmans JM, Peremans L, Menni M, et al. Structured reporting: if, why,
when, how-and at what expense? Results of a focus group meeting of
radiology professionals from eight countries. Insights Imaging 2012; 3:295–
302.
12. Weiss DL, Langlotz CP. Structured reporting: patient care enhance-
ment or productivity nightmare? Radiology 2008; 249:739–747.
13. Bosmans JM, Neri E, Ratib O, et al. Structured reporting: a fusion reactor
hungry for fuel. Insights Imaging 2015; 6:129–132.
14. Bender LC, Linnau KF, Meier EN, et al. Interrater agreement in the eval-
uation of discrepant imaging findings with the Radpeer system. AJR Am
J Roentgenol 2012; 199:1320–1327.
15. Borgstede JP, Lewis RS, Bhargavan M, et al. RADPEER quality assur-
ance program: a multifacility study of interpretive disagreement rates.
Journal of the American College of Radiology : JACR. 2004; 1:59–65.
16. Donald JJ, Barnard SA. Common patterns in 558 diagnostic radiology
errors. J Med Imaging Radiat Oncol 2012; 56:173–178.
17. Hsu W, Han SX, Arnold CW, et al. A data-driven approach for quality
assessment of radiologic interpretations. J Am Med Inform Assoc 2016;
23(e1):e152–e156.
18. McCreadie G, Oliver TB. Eight CT lessons that we learned the hard way:
an analysis of current patterns of radiological error and discrepancy with
particular emphasis on CT. Clin Radiol 2009; 64:491–499, discussion 500–
501.
19. Berlin L, Berlin JW. Malpractice and radiologists in Cook County, IL: trends
in 20 years of litigation. AJR Am J Roentgenol 1995; 165:781–788.
20. Halpin SF. Medico-legal claims against English radiologists: 1995–
2006. Br J Radiol 2009; 82:982–988.
21. Pinto A, Acampora C, Pinto F, et al. Learning from diagnostic errors:
a good way to improve education in radiology. Eur J Radiol 2011; 78:372–
376.
22. Thomson NB, 3rd, Patel M. Radiology liability update: review of claims,
trends, high-risk conditions and practices, and tort reform alternatives.
J Am Coll Radiol 2012; 9:729–733.
23. Lee CS, Nagy PG, Weaver SJ, et al. Cognitive and system factors con-
tributing to diagnostic errors in radiology. AJR Am J Roentgenol 2013;
201:611–617.
24. Graber ML, Wachter RM, Cassel CK. Bringing diagnosis into the quality
and safety equations. JAMA 2012; 308:1211–1212.
25. Lin E, Powell DK, Kagetsu NJ. Efficacy of a checklist-style structured
radiology reporting template in reducing resident misses on cervical spine
computed tomography examinations. J Digit Imaging 2014; 27:588–
593.
26. Quattrocchi CC, Giona A, Di Martino AC, et al. Extra-spinal incidental
findings at lumbar spine MRI in the general population: a large cohort
study. Insights Imaging 2013; 4:301–308.
27. Semaan HB, Bieszczad JE, Obri T, et al. Incidental extraspinal findings
at lumbar spine magnetic resonance imaging: a retrospective study. Spine
2015; 40:1436–1443.
28. McKee BJ, Regis SM, McKee AB, et al. Performance of ACR Lung-
RADS in a clinical CT lung screening program. J Am Coll Radiol 2015;
12:273–276.
29. Rosskopf AB, Dietrich TJ, Hirschmann A, et al. Quality management in
musculoskeletal imaging: form, content, and diagnosis of knee MRI reports
7
GANESHAN ET AL
and effectiveness of three different quality improvement measures. AJR
Am J Roentgenol 2015; 204:1069–1074.
30. Ghoshhajra BB, Lee AM, Ferencik M, et al. Interpreting the interpreta-
tions: the use of structured reporting improves referring clinicians’
comprehension of coronary CT angiography reports. J Am Coll Radiol
2013; 10:432–438.
31. Brook OR, Brook A, Vollmer CM, et al. Structured reporting of multipha-
sic CT for pancreatic cancer: potential effect on staging and surgical
planning. Radiology 2015; 274:464–472.
32. Marcal LP, Fox PS, Evans DB, et al. Analysis of free-form radiology dic-
tations for completeness and clarity for pancreatic cancer staging. Abdom
Imaging 2015; 40:2391–2397.
33. Sahni VA, Silveira PC, Sainani NI, et al. Impact of a structured report tem-
plate on the quality of MRI reports for rectal cancer staging. AJR Am J
Roentgenol 2015; 205:584–588.
34. Gunn AJ, Alabre CI, Bennett SE, et al. Structured feedback from refer-
ring physicians: a novel approach to quality improvement in radiology
reporting. AJR Am J Roentgenol 2013; 201:853–857.
35. Hawkins CM, Hall S, Hardin J, et al. Prepopulated radiology report tem-
plates: a prospective analysis of error rate and turnaround time. J Digit
Imaging 2012; 25:504–511.
36. McGurk S, Brauer K, Macfarlane TV, et al. The effect of voice recogni-
tion software on comparative error rates in radiology reports. Br J Radiol
2008; 81:767–770.
37. Hawkins CM, Hall S, Zhang B, et al. Creation and implementation of
department-wide structured reports: an analysis of the impact on error
rate in radiology reports. J Digit Imaging 2014; 27:581–587.
38. Duszak R, Jr, Nossal M, Schofield L, et al. Physician documentation de-
ficiencies in abdominal ultrasound reports: frequency, characteristics, and
financial impact. J Am Coll Radiol 2012; 9:403–408.
39. Faggioni L, Coppola F, Ferrari R, et al. Usage of structured reporting in
radiological practice: results from an Italian online survey. Eur Radiol 2017;
27:1934–1943.
40. Powell DK, Silberzweig JE. State of structured reporting in radiology, a
survey. Acad Radiol 2015; 22:226–233.
41. Bosmans JM, Weyler JJ, De Schepper AM, et al. The radiology report
as seen by radiologists and referring clinicians: results of the COVER and
ROVER surveys. Radiology 2011; 259:184–195.
42. Gunderman RB, McNeive LR. Is structured reporting the answer? Ra-
diology 2014; 273:7–9.
43. Srinivasa Babu A, Brooks ML. The malpractice liability of radiology reports:
minimizing the risk. Radiographics 2015; 35:547–554.
44. Winter TC. The propaedeutics of structured reporting. Radiology 2015;
275:309–310.
45. Hall FM. The radiology report of the future. Radiology 2009; 251:313–
316.
46. Manoonchai N, Kaewlai R, Wibulpolprasert A, et al. Satisfaction of imaging
report rendered in emergency setting: a survey of radiology and refer-
ring physicians. Acad Radiol 2015; 22:760–770.
47. Krupinski EA, Hall ET, Jaw S, et al. Influence of radiology report format
on reading time and comprehension. J Digit Imaging 2012; 25:63–69.
48. Sistrom CL, Honeyman-Buck J. Free text versus structured format: in-
formation transfer efficiency of radiology reports. AJR Am J Roentgenol
2005; 185:804–812.
49. Johnson AJ, Chen MY, Swan JS, et al. Cohort study of structured re-
porting compared with conventional dictation. Radiology 2009; 253:74–
80.
50. Vache T, Bratan F, Mege-Lechevallier F, et al. Characterization of pros-
tate lesions as benign or malignant at multiparametric MR imaging:
comparison of three scoring systems in patients treated with radical pros-
tatectomy. Radiology 2014; 272:446–455.
51. Houssami N, Boyages J, Stuart K, et al. Quality of breast imaging reports
falls short of recommended standards. Breast 2007; 16:271–279.
Academic Radiology, Vol ■, No ■■, ■■ 2017
52. Margolies LR, Pandey G, Horowitz ER, et al. Breast imaging in the era
of big data: structured reporting and data mining. AJR Am J Roentgenol
2016; 206:259–264.
53. Radiology reporting initiative. Available at: https://www.rsna.org/
Reporting_Initiative.aspx. Accessed May 1, 2017.
54. Morgan TA, Helibrun ME, Kahn CE, Jr. Reporting initiative of the Radio-
logical Society of North America: progress and new directions. Radiology
2014; 273:642–645.
55. RadReport template library. Available at: http://www.radreport.org/. Ac-
cessed May 1, 2017.
56. Al-Hawary MM, Francis IR, Chari ST, et al. Pancreatic ductal adenocar-
cinoma radiology reporting template: consensus statement of the Society
of Abdominal Radiology and the American Pancreatic Association. Gas-
troenterology 2014; 146:291–304, e1.
57. Larson DB, Towbin AJ, Pryor RM, et al. Improving consistency in radi-
ology reporting through the use of department-wide standardized
structured reporting. Radiology 2013; 267:240–250.
58. Anderson TJ, Lu N, Brook OR. Disease-specific report templates for your
practice. J Am Coll Radiol 2017; 14:1055–1057.
59. Goldberg-Stein S, Walter WR, Amis ES, Jr, et al. Implementing a struc-
tured reporting initiative using a collaborative multistep approach. Curr
Probl Diagn Radiol 2016; 46:295–299.
60. 2016 radiology preferred specialty measure set. Available at:
https://www.cms.gov/Medicare/Quality-Initiatives-Patient-Assessment
-Instruments/PQRS/downloads/Radiology_Specialty_Measure_Set.pdf.
Accessed May 1, 2017.
61. Choksi VR, Marn CS, Bell Y, et al. Efficiency of a semiautomated coding
and review process for notification of critical findings in diagnostic imaging.
AJR Am J Roentgenol 2006; 186:933–936.
62. Zafar HM, Chadalavada SC, Kahn CE, Jr, et al. Code abdomen: an as-
sessment coding scheme for abdominal imaging findings possibly
representing cancer. J Am Coll Radiol 2015; 12:947–950.
63. Sevenster M, Travis AR, Ganesh RK, et al. Improved efficiency in clini-
cal workflow of reporting measured oncology lesions via PACS-
integrated lesion tracking tool. AJR Am J Roentgenol 2015; 204:576–
583.
64. Zimmerman SL, Kim W, Boonn WW. Informatics in radiology: auto-
mated structured reporting of imaging findings using the AIM standard
and XML. Radiographics 2011; 31:881–887.
65. Alkasab TK, Bizzo BC, Berland LL, et al. Creation of an open frame-
work for point-of-care computer-assisted reporting and decision support
tools for radiologists. J Am Coll Radiol 2017; 14:1184–1189.
66. Taylor AT, Garcia EV. Computer-assisted diagnosis in renal nuclear med-
icine: rationale, methodology, and interpretative criteria for diuretic
renography. Semin Nucl Med 2014; 44:146–158.
67. Wang KC, Jeanmenne A, Weber GM, et al. An online evidence-based
decision support system for distinguishing benign from malignant ver-
tebral compression fractures by magnetic resonance imaging feature
analysis. J Digit Imaging 2011; 24:507–515.
68. Sadigh G, Hertweck T, Kao C, et al. Traditional text-only versus multimedia-
enhanced radiology reporting: referring physicians’ perceptions of value.
J Am Coll Radiol 2015; 12:519–524.
69. Nayak L, Beaulieu CF, Rubin DL, et al. A picture is worth a thousand
words: needs assessment for multimedia radiology reports in a large ter-
tiary care medical center. Acad Radiol 2013; 20:1577–1583.
70. Oh SC, Cook TS, Kahn CE, Jr. PORTER: a prototype system for
patient-oriented radiology reporting. J Digit Imaging 2016; 29:450–
454.
71. Vining D, Salem U, Duran C, et al., Development of the ViSion Ontol-
ogy for Structured Reporting. Radiological Society of North America 2013
Scientific Assembly and Annual Meeting, December 1–December 6, 2013,
Chicago IL. Available at: http://archive.rsna.org/2013/13023813.html. Ac-
cessed April 21, 2017.