122:
244:
25:
360:, regions of interest (ROIs) hierarchically encompass pages, text or graphical blocks, down to individual line-strip images, word and character image boxes. The de facto standard in archives and libraries is the tuplet {image_file, xml_file}, usually in the form of a *.tif file and its accompanying *.xml file.
149:, the boundaries of a tumor may be defined on an image or in a volume, for the purpose of measuring its size. The endocardial border may be defined on an image, perhaps during different phases of the cardiac cycle, for example, end-systole and end-diastole, for the purpose of assessing cardiac function. In
278:
Structured data may be encoded in a separate object as a structured report in the form of a tree of name-value pairs of coded or text concepts possibly associated with derived quantitative information can reference spatial and/or temporal coordinates that in turn reference the image objects to which
293:
encoded in a segmentation object as either binary or probabilistic values in a raster (which is not required to have the same spatial sampling or extent as the images from which the segmentation was derived); these are usually referenced by other objects containing structured content (structured
317:
Structured data may be encoded in a separate object as a structured report in the form of a tree of name-value pairs of coded or text concepts possibly associated with derived quantitative information can reference temporal coordinates that in turn reference the waveform objects to which they
302:
Contours of objects may be defined as structure sets, either as pixel coordinates by reference to specific images or as coordinates in a named patient-relative 3D Cartesian space (these are also used for non-RT
275:
Unstructured vector graphics and text as well as bitmap (rasterized) overlay graphics may be encoded in a separate object as a presentation state that references the image object to which it is to be applied
286:
in the form of spatial coordinates with an associated coded purpose, either as pixel coordinates by reference to specific images or as coordinates in a named patient-relative 3D Cartesian space
212:
As an integral part of the sample data set, with a unique or masking value that may or may not be outside the normal range of normally occurring values and which tags individual data cells
328:
also has a subset of mechanisms similar to (and intended to be compatible with) DICOM for referencing image-related spatial coordinates as observations; it allows for a circle, ellipse,
332:
or point to be defined as integer pixel-relative coordinates referencing an external multi-media image object, which may be of a consumer rather than medical image format (e.g., a
165:
of an object under consideration. In many applications, symbolic (textual) labels are added to a ROI, to describe its content in a compact manner. Within a ROI may lie individual
247:
The left image shows an original mammogram before MED-SEG processing. The image on the right, with region of interest (white) labeled, shows a mammogram after MED-SEG processing.
205:, often associated with categorical or quantitative information (e.g., measurements like volume or mean intensity), expressed as text or in a structured form.
145:
identified for a particular purpose. The concept of a ROI is commonly used in many application areas. Existing as a vicinity, or within one. For example, in
314:
Annotations may be encoded in a separate attribute can select multiple time points or a range of time points, either by sample number or specified time
454:
449:
422:
215:
As separate, purely graphic information, such as with vector or bitmap (rasterized) drawing elements, perhaps with some accompanying plain
269:
Bitmap (rasterized) overlay graphics and text may be present in unused high bits of the pixel data or in a separate attribute (deprecated)
42:
388:
specifically provide mechanisms to label and/or compress to a different degree of fidelity, what they refer to as regions of interest.
108:
89:
150:
61:
325:
46:
353:
158:
68:
384:) drawing file formats that are widely available, and which carry no specific ROI semantics, some standards such as
75:
35:
337:
444:
377:
357:
57:
368:
As far as non-medical standards are concerned, in addition to the purely graphic markup languages (such as
126:
231:
82:
418:
414:
216:
167:
197:
4D dataset: the outline of an object at or during a particular time interval in a time-volume
283:
154:
146:
162:
438:
407:
290:
272:
Vector graphics may be encoded in separate image attributes as curves (deprecated)
255:
provide general and application-specific mechanisms to support various use-cases.
243:
186:
3D dataset: the contours or surfaces outlining an object (sometimes known as the
121:
24:
153:(GIS), a ROI can be taken literally as a polygonal selection from a 2D map. In
369:
227:
202:
385:
329:
223:
142:
263:
252:
242:
120:
208:
There are three fundamentally different means of encoding a ROI:
381:
341:
373:
333:
322:
18:
16:
Samples within a data set identified for a particular purpose
266:
value range (e.g., as the maximum white value) (deprecated)
311:
Burned in values may occur with the waveform (deprecated)
289:
Pixels (possibly non-contiguous) may be classified into
262:
Burned in graphics and text may occur within the normal
180:
1D dataset: a time or frequency interval on a waveform
183:
2D dataset: the boundaries of an object on an image
49:. Unsourced material may be challenged and removed.
406:
8:
258:For DICOM images (two or more dimensions):
409:The Art and Science of Digital Compositing
109:Learn how and when to remove this message
397:
282:Reference locations may be encoded as
219:text in the format of the data itself
7:
47:adding citations to reliable sources
251:Medical imaging standards such as
14:
125:The region of interest for which
307:For DICOM time-based waveforms:
151:geographical information systems
23:
175:Examples of regions of interest
34:needs additional citations for
455:Geographic information systems
376:) and vector graphic (such as
326:Clinical Document Architecture
1:
450:Optical character recognition
354:Optical Character Recognition
159:optical character recognition
413:. Morgan Kaufmann. pp.
234:and/or temporal coordinates
226:information (such as coded
471:
348:Document analysis systems
222:As a separate structured
358:Document Layout Analysis
298:For DICOM radiotherapy:
141:) is a sample within a
405:Ron Brinkmann (1999).
248:
161:, the ROI defines the
130:
364:Other 2D applications
246:
124:
129:gives a lower bound.
58:"Region of interest"
43:improve this article
201:A ROI is a form of
137:(often abbreviated
127:Markov's inequality
380:) and 3D (such as
249:
188:Volume of Interest
168:points of interest
135:region of interest
131:
424:978-0-12-133960-9
119:
118:
111:
93:
462:
429:
428:
412:
402:
230:) with a set of
114:
107:
103:
100:
94:
92:
51:
27:
19:
470:
469:
465:
464:
463:
461:
460:
459:
445:Medical imaging
435:
434:
433:
432:
425:
404:
403:
399:
394:
366:
350:
241:
239:Medical imaging
177:
155:computer vision
147:medical imaging
115:
104:
98:
95:
52:
50:
40:
28:
17:
12:
11:
5:
468:
466:
458:
457:
452:
447:
437:
436:
431:
430:
423:
396:
395:
393:
390:
365:
362:
349:
346:
320:
319:
315:
312:
305:
304:
296:
295:
287:
280:
276:
273:
270:
267:
240:
237:
236:
235:
220:
217:(unstructured)
213:
199:
198:
195:
194:)) in a volume
184:
181:
176:
173:
117:
116:
99:September 2012
31:
29:
22:
15:
13:
10:
9:
6:
4:
3:
2:
467:
456:
453:
451:
448:
446:
443:
442:
440:
426:
420:
416:
411:
410:
401:
398:
391:
389:
387:
383:
379:
375:
371:
363:
361:
359:
355:
347:
345:
343:
339:
335:
331:
327:
324:
316:
313:
310:
309:
308:
303:applications)
301:
300:
299:
292:
288:
285:
281:
277:
274:
271:
268:
265:
261:
260:
259:
256:
254:
245:
238:
233:
229:
225:
221:
218:
214:
211:
210:
209:
206:
204:
196:
193:
189:
185:
182:
179:
178:
174:
172:
170:
169:
164:
160:
156:
152:
148:
144:
140:
136:
128:
123:
113:
110:
102:
91:
88:
84:
81:
77:
74:
70:
67:
63:
60: –
59:
55:
54:Find sources:
48:
44:
38:
37:
32:This article
30:
26:
21:
20:
408:
400:
367:
351:
321:
306:
297:
257:
250:
207:
200:
191:
187:
166:
138:
134:
132:
105:
96:
86:
79:
72:
65:
53:
41:Please help
36:verification
33:
228:value types
439:Categories
392:References
370:PostScript
356:(OCR) and
279:they apply
203:Annotation
69:newspapers
386:JPEG 2000
284:fiducials
330:polyline
294:reports)
291:segments
224:semantic
171:(POIs).
143:data set
232:spatial
163:borders
83:scholar
421:
85:
78:
71:
64:
56:
318:apply
264:pixel
253:DICOM
90:JSTOR
76:books
419:ISBN
382:VRML
342:JPEG
157:and
62:news
415:184
378:SVG
374:PDF
372:or
352:In
344:).
340:or
338:PNG
334:GIF
323:HL7
192:VOI
139:ROI
45:by
441::
417:.
336:,
133:A
427:.
190:(
112:)
106:(
101:)
97:(
87:·
80:·
73:·
66:·
39:.
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.
