Image processing method and apparatus

• US 7,957,571 B2
• Filed: 07/10/2007
• Issued: 06/07/2011
• Est. Priority Date: 05/27/2003
• Status: Expired due to Fees

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Tsujii, Osamu
• Primary Examiner(s): Strege; John B
• Application Number:
  US11/775,470
• Publication Number:
  US 20080015902A1
• Time in Patent Office: 1,428 Days
• Field of Search: 382/128, 382/130, 382/131
• US Class Current: 382/128
• CPC Class Codes: G16H 30/40 for processing medical images, e.g. editing
• CPC Class Codes: G16H 70/60 relating to pathologies

Abstract

In step S1, image data obtained by imaging is input to an image input unit (1). In step S2, the diagnosis result obtained by a doctor using the image data obtained by imaging is input as diagnosis information to a diagnosis information input unit (2). In step S3, a keyword table (7) is searched for a keyword input to the diagnosis information input unit (2) or a diagnosis information analyzing unit (3). In step S4, a parameter determining unit (5) selects an initial value parameter used in an image search unit (4) from an initial value table (8) on the basis of the input keyword. In steps S5 and S6, the image search unit (4) determines the optimization degree of the selected parameter by applying the parameter to the input image on the basis of the area or connectivity of a morbid region, and also extracts a morbid region by using a general computer aided diagnosis technique.

Claims

1. An image processing apparatus comprising:

a first obtaining unit which obtains a plurality of CT or MRI images obtained by imaging;

a second obtaining unit which obtains diagnosis information;

an analyzing unit which searches a keyword from the diagnosis information;

a determining unit which restricts a CT or MRI value range for searching a lesion candidate based on the searched keyword; and

an extracting unit which extracts a morbid region from the lesion candidate searched from the restricted CT or MRI value range of the CT or MRI images.

2. The apparatus according to claim 1, wherein the second obtaining unit comprises a keyword obtaining unit which obtains the keyword for analysis of text input by an input unit, and

wherein the CT or MRI value range for searching the lesion candidate is changed on the basis of the searched keyword.

3. The apparatus according to claim 1, wherein at least one of each CT value/MRI value range for the CT or MRI image, each CT value/MRI value range which designates a lesion, and a slice position is changed as the CT or MRI value range.

4. The apparatus according to claim 3, further comprising a table in which the keyword and a parameter are associated,

wherein the parameter is obtained from the table in which the parameter is associated with the CT or MRI value range.

7. The apparatus according to claim 1, further comprising a unit which corrects the CT or MRI value on the basis of connectivity of the obtained CT or MRI images with the CT or MRI value range.

5. An image processing method comprising:

a first obtaining step of obtaining a plurality of CT or MRI images obtained by imaging;

a second obtaining step of obtaining diagnosis information;

an analyzing step of searching a keyword from the diagnosis information;

a determining step of restricting a CT or MRI value range for searching a lesion candidate based on the searched keyword; and

an extracting step of extracting a morbid region from the lesion candidate searched from the restricted CT or MRI value range of the CT or MRI images.

6. A non-transitory computer readable medium storing thereon a computer-executable program comprising:

a code for a first obtaining step of obtaining a plurality of CT or MRI images obtained by imaging;

a code for a second obtaining step of obtaining diagnosis information;

a code for an analyzing step of searching a keyword from the diagnosis information;

a code for a determining step of restricting a CT or MRI value range for searching a lesion candidate based on the searched keyword; and

a code for an extracting step of extracting a morbid region from the lesion candidate searched from the restricted CT or MRI value range of the CT or MRI images.